cache/agreements_cache_7b814a45375ad6b75add8b396f69c2cd.csv

scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.1111111111111111,0.7274895282186948
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,-0.1111111111111111,0.7274895282186948
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.28888888888888886,0.2912483465608466
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.24444444444444444,0.38071979717813054
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.37777777777777777,0.1557418430335097
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.1111111111111111,0.7274895282186948
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,-0.06666666666666667,0.8618005952380953
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.19999999999999998,0.4843127204585538
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.1111111111111111,0.7274895282186948
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.06666666666666667,0.8618005952380953
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.19999999999999998,0.4843127204585538
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.6440611887195306,0.01102341638822145
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.40451991747794525,0.1059975484249457
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.6440611887195306,0.01102341638822145
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.24444444444444444,0.38071979717813054
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.24444444444444444,0.38071979717813054
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.24444444444444444,0.38071979717813054
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.15555555555555553,0.6006536596119929
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.3333333333333333,0.21637345679012346
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8090398349558905,0.0012254240706707103
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8989331499509894,0.0003280163150135276
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.49441323247304414,0.048193488293190756
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.022222222222222223,1.0
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.5393598899705937,0.03114121059579671
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8539864924534399,0.0006436975254696865
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6137949055234262,0.01491204965521593
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.522862326927363,0.03809415806109578
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8989331499509894,0.0003280163150135276
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6741998624632421,0.0070583320485280866
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.5843065474681431,0.019550269092885535
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.15555555555555553,0.6006536596119929
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.37777777777777777,0.1557418430335097
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.19999999999999998,0.4843127204585538
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,-0.08989331499509894,0.7194375444233914
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.34099716973523675,0.17621399555130546
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.4600437062282361,0.06941907499936387
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4222222222222222,0.10831349206349207
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.5843065474681431,0.019550269092885535
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.19999999999999998,0.4843127204585538
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.3333333333333333,0.21637345679012346
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.37777777777777777,0.1557418430335097
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.37777777777777777,0.1557418430335097
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5843065474681431,0.019550269092885535
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6741998624632421,0.0070583320485280866
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.5843065474681431,0.019550269092885535
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6137949055234262,0.01491204965521593
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.5555555555555555,0.02860945767195767
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.40451991747794525,0.1059975484249457
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8539864924534399,0.0006436975254696865
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.40451991747794525,0.1059975484249457
MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.49441323247304414,0.048193488293190756
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.40451991747794525,0.1059975484249457
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.5843065474681431,0.019550269092885535
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8989331499509894,0.0003280163150135276
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8090398349558905,0.0012254240706707103
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7191465199607915,0.004057136032371292
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.28888888888888886,0.2912483465608466
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.4666666666666666,0.07255015432098766
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.40451991747794525,0.1059975484249457
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.1111111111111111,0.7274895282186948
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.06666666666666667,0.8618005952380953
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.1111111111111111,0.7274895282186948
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.3333333333333333,0.21637345679012346
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953
OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829
OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.3333333333333333,0.21637345679012346
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.37777777777777777,0.1557418430335097
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097
OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6292532049656926,0.011921001496914019
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767
OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.4666666666666666,0.07255015432098766
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766
OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.06666666666666667,0.8618005952380953
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.26967994498529685,0.2811980995641792
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.35957325998039574,0.15076277502664528
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.5393598899705937,0.03114121059579671
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.22473328748774735,0.36917141633269157
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.3146266024828463,0.2086677876982641
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.28888888888888886,0.2912483465608466
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.5393598899705937,0.03114121059579671
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.3146266024828463,0.2086677876982641
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9320589306096472,0.00021829510003985143
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.9320589306096472,0.00021829510003985143
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7640931774583409,0.002263469812035174
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767
WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8989331499509894,0.0003280163150135276
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8989331499509894,0.0003280163150135276
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.06666666666666667,0.8618005952380953
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.35957325998039574,0.15076277502664528
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.49441323247304414,0.048193488293190756
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.15555555555555553,0.6006536596119929
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6292532049656926,0.011921001496914019
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.4222222222222222,0.10831349206349207
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7501937734175208,0.0029250200956793346
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6292532049656926,0.011921001496914019
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.5520524474738833,0.029345108174841844
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.7640931774583409,0.002263469812035174
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829
BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8090398349558905,0.0012254240706707103
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766
BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.3146266024828463,0.2086677876982641
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7501937734175208,0.0029250200956793346
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.35957325998039574,0.15076277502664528
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6741998624632421,0.0070583320485280866
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097
BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067
BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7047274841194893,0.005187148855929351
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9438798074485389,0.0001621317520439264
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7047274841194893,0.005187148855929351
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7047274841194893,0.005187148855929351
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9438798074485389,0.0001621317520439264
LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.5393598899705937,0.03114121059579671
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552
LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.1111111111111111,0.7274895282186948
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.4494665749754947,0.07248608508684644
Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7640931774583409,0.002263469812035174
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,1,0.9775252199076787,0.00010567442661664933
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,4,0.8865926413116155,0.000437257592706733
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188
BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,2,0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,3,-0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,4,-0.28888888888888886,0.2912483465608466
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,5,0.24444444444444444,0.38071979717813054
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,7,-0.37777777777777777,0.1557418430335097
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0
aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,0,0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,2,-0.06666666666666667,0.8618005952380953
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,3,0.19999999999999998,0.4843127204585538
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,4,-0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,7,-0.4222222222222222,0.10831349206349207
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0
aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,7,-0.06666666666666667,0.8618005952380953
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,8,0.19999999999999998,0.4843127204585538
aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,4,0.6440611887195306,0.01102341638822145
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,7,0.40451991747794525,0.1059975484249457
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,8,0.6440611887195306,0.01102341638822145
aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,4,0.24444444444444444,0.38071979717813054
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,7,0.24444444444444444,0.38071979717813054
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953
aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,2,0.24444444444444444,0.38071979717813054
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,7,-0.15555555555555553,0.6006536596119929
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346
aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,0,0.8090398349558905,0.0012254240706707103
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,3,0.8989331499509894,0.0003280163150135276
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,7,0.49441323247304414,0.048193488293190756
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,7,0.022222222222222223,1.0
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,8,0.5393598899705937,0.03114121059579671
aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8539864924534399,0.0006436975254696865
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6137949055234262,0.01491204965521593
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.522862326927363,0.03809415806109578
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8989331499509894,0.0003280163150135276
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6741998624632421,0.0070583320485280866
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.5843065474681431,0.019550269092885535
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.15555555555555553,0.6006536596119929
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.19999999999999998,0.4843127204585538
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,1,-0.08989331499509894,0.7194375444233914
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.34099716973523675,0.17621399555130546
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.4600437062282361,0.06941907499936387
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4222222222222222,0.10831349206349207
aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.5843065474681431,0.019550269092885535
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.19999999999999998,0.4843127204585538
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.3333333333333333,0.21637345679012346
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,1,0.5843065474681431,0.019550269092885535
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,7,0.6741998624632421,0.0070583320485280866
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,8,0.5843065474681431,0.019550269092885535
aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6137949055234262,0.01491204965521593
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,4,0.40451991747794525,0.1059975484249457
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,5,0.8539864924534399,0.0006436975254696865
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,8,0.40451991747794525,0.1059975484249457
aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,1,0.49441323247304414,0.048193488293190756
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,3,0.40451991747794525,0.1059975484249457
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,4,0.5843065474681431,0.019550269092885535
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,5,0.8989331499509894,0.0003280163150135276
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,9,0.8090398349558905,0.0012254240706707103
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,0,0.40451991747794525,0.1059975484249457
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,1,0.1111111111111111,0.7274895282186948
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,5,0.06666666666666667,0.8618005952380953
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,6,0.1111111111111111,0.7274895282186948
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953
aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,5,0.3333333333333333,0.21637345679012346
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,6,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,6,0.6292532049656926,0.011921001496914019
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,9,0.06666666666666667,0.8618005952380953
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,0,0.26967994498529685,0.2811980995641792
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,1,0.35957325998039574,0.15076277502664528
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,4,0.22473328748774735,0.36917141633269157
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,5,0.3146266024828463,0.2086677876982641
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792
aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,9,0.3146266024828463,0.2086677876982641
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,6,0.9320589306096472,0.00021829510003985143
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,7,0.9320589306096472,0.00021829510003985143
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,9,0.7640931774583409,0.002263469812035174
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8989331499509894,0.0003280163150135276
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8989331499509894,0.0003280163150135276
aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.06666666666666667,0.8618005952380953
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.35957325998039574,0.15076277502664528
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.49441323247304414,0.048193488293190756
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.15555555555555553,0.6006536596119929
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6292532049656926,0.011921001496914019
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792
aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,7,0.7501937734175208,0.0029250200956793346
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,9,0.6292532049656926,0.011921001496914019
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,1,0.5520524474738833,0.029345108174841844
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,4,0.7640931774583409,0.002263469812035174
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,5,0.8090398349558905,0.0012254240706707103
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,2,0.3146266024828463,0.2086677876982641
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,3,0.7501937734175208,0.0029250200956793346
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,7,0.35957325998039574,0.15076277502664528
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,6,0.6741998624632421,0.0070583320485280866
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097
aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,0,0.7047274841194893,0.005187148855929351
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,1,0.9438798074485389,0.0001621317520439264
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,5,0.7047274841194893,0.005187148855929351
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,7,0.7047274841194893,0.005187148855929351
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,8,0.9438798074485389,0.0001621317520439264
aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,2,0.5393598899705937,0.03114121059579671
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,7,0.1111111111111111,0.7274895282186948
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,8,0.4494665749754947,0.07248608508684644
aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,1,0.9775252199076787,0.00010567442661664933
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,4,0.8865926413116155,0.000437257592706733
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06