JavaBench / data /data_method.json
CPunisher's picture
Data
23f22ff
{
"completion": [
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-4o-2024-05-13",
"Pass_at_1": 1.0
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.9378571429
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.9357142857
},
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.9214285714
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.8642857143
},
{
"Context": "selective",
"Method": "independent",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.8535714286
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.8471428571
},
{
"Context": "selective",
"Method": "holistic",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.845
},
{
"Context": "selective",
"Method": "incremental",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.8392857143
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.8192857143
},
{
"Context": "selective",
"Method": "holistic",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.7964285714
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.7485714286
},
{
"Context": "selective",
"Method": "independent",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.6378571429
},
{
"Context": "selective",
"Method": "incremental",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.5992857143
},
{
"Context": "selective",
"Method": "independent",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.5971428571
},
{
"Context": "selective",
"Method": "incremental",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.5057142857
}
],
"compilation_class_wise": [
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.7942857143
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.7414285714
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.725
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.7171428571
},
{
"Context": "selective",
"Method": "incremental",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.7
},
{
"Context": "selective",
"Method": "holistic",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.6978571429
},
{
"Context": "selective",
"Method": "independent",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.6828571429
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.6814285714
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.6764285714
},
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-4o-2024-05-13",
"Pass_at_1": 0.6607142857
},
{
"Context": "selective",
"Method": "holistic",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.58
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.5778571429
},
{
"Context": "selective",
"Method": "incremental",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.5021428571
},
{
"Context": "selective",
"Method": "independent",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.4985714286
},
{
"Context": "selective",
"Method": "independent",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.4335714286
},
{
"Context": "selective",
"Method": "incremental",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.3507142857
}
],
"compilation_test_wise": [
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-4o-2024-05-13",
"Pass_at_1": 0.5035714286
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.4202826585
},
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.3443277311
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.3378676471
},
{
"Context": "selective",
"Method": "holistic",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.3183823529
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.3121848739
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.2836134454
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.2621848739
},
{
"Context": "selective",
"Method": "holistic",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.2240546218
},
{
"Context": "selective",
"Method": "independent",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.1930147059
},
{
"Context": "selective",
"Method": "incremental",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.0955357143
},
{
"Context": "selective",
"Method": "independent",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.0932773109
},
{
"Context": "selective",
"Method": "incremental",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.0701680672
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.0352941176
},
{
"Context": "selective",
"Method": "independent",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.0
},
{
"Context": "selective",
"Method": "incremental",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.0
}
],
"pass_class_wise": [
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.7832360347
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.723699056
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.7036481325
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.6855203826
},
{
"Context": "selective",
"Method": "incremental",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.6846699639
},
{
"Context": "selective",
"Method": "holistic",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.6808480861
},
{
"Context": "selective",
"Method": "independent",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.6772858762
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.6547244155
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.6547232007
},
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-4o-2024-05-13",
"Pass_at_1": 0.6545897285
},
{
"Context": "selective",
"Method": "holistic",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.5674101922
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.5603969625
},
{
"Context": "selective",
"Method": "incremental",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.4878321662
},
{
"Context": "selective",
"Method": "independent",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.4863639752
},
{
"Context": "selective",
"Method": "independent",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.4261740357
},
{
"Context": "selective",
"Method": "incremental",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.3468474087
}
],
"pass_test_wise": [
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-4o-2024-05-13",
"Pass_at_1": 0.3438179726
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.3047552867
},
{
"Context": "selective",
"Method": "holistic",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.2941156144
},
{
"Context": "selective",
"Method": "holistic",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.2544265255
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.2224382166
},
{
"Context": "selective",
"Method": "independent",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.2083516025
},
{
"Context": "selective",
"Method": "holistic",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.2028454735
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-6.7b-instruct",
"Pass_at_1": 0.1967821219
},
{
"Context": "selective",
"Method": "independent",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.1930147059
},
{
"Context": "selective",
"Method": "holistic",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.1669267449
},
{
"Context": "selective",
"Method": "independent",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.0714792814
},
{
"Context": "selective",
"Method": "incremental",
"Model": "Phind-CodeLlama-34B-v2",
"Pass_at_1": 0.061012122
},
{
"Context": "selective",
"Method": "incremental",
"Model": "gpt-3.5-turbo-1106",
"Pass_at_1": 0.0514928193
},
{
"Context": "selective",
"Method": "incremental",
"Model": "deepseek-coder-33b-instruct",
"Pass_at_1": 0.0350620781
},
{
"Context": "selective",
"Method": "independent",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.0
},
{
"Context": "selective",
"Method": "incremental",
"Model": "WizardCoder-15B-V1.0",
"Pass_at_1": 0.0
}
]
}