Update model_performance.csv
Browse files- model_performance.csv +17 -17
model_performance.csv
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
Models,Average,FinQA,DM-Simplong,XBRL-Math,Type
|
2 |
-
GPT-4o,68.24,72.49,60.0,72.22,
|
3 |
-
GPT-o1,59.84,49.07,56.0,74.44,
|
4 |
-
GPT-o3-mini,65.51,60.87,59.0,76.67,
|
5 |
-
DeepSeek-V3,67.62,73.2,53.0,76.67,
|
6 |
-
DeepSeek-R1,68.93,65.13,53.0,86.67,
|
7 |
-
Qwen2.5-72B-Instruct,66.72,73.38,59.0,67.78,
|
8 |
-
Qwen2.5-72B-Instruct-Math,65.69,69.74,42.0,83.33,
|
9 |
-
DeepSeek-R1-Distill-Llama-70B,68.8,66.73,53.0,86.67,
|
10 |
-
Llama3-70B-Instruct,52.2,58.92,41.0,56.67,
|
11 |
-
Llama3.1-70B-Instruct,58.17,63.18,48.0,63.33,
|
12 |
-
Llama3.3-70B-Instruct,64.05,68.15,54.0,70.0,
|
13 |
-
DeepSeek-R1-Distill-Qwen-32B,68.97,65.48,55.0,84.44,
|
14 |
-
DeepSeek-R1-Distill-Qwen-14B,63.9,63.27,44.0,84.44,
|
15 |
-
DeepSeek-R1-Distill-Llama-8B,53.36,45.96,33.0,81.11,
|
16 |
-
Llama3-8B-Instruct,39.95,41.97,29.0,48.89,
|
17 |
-
Llama3.1-8B-Instruct,50.12,54.13,34.0,62.22,
|
18 |
-
Fino1-8B,61.03,60.87,40.0,82.22,
|
|
|
1 |
Models,Average,FinQA,DM-Simplong,XBRL-Math,Type
|
2 |
+
GPT-4o,68.24,72.49,60.0,72.22,Instruction-tuned
|
3 |
+
GPT-o1,59.84,49.07,56.0,74.44,Reasoning-enhanced
|
4 |
+
GPT-o3-mini,65.51,60.87,59.0,76.67,Reasoning-enhanced
|
5 |
+
DeepSeek-V3,67.62,73.2,53.0,76.67,Instruction-tuned
|
6 |
+
DeepSeek-R1,68.93,65.13,53.0,86.67,Reasoning-enhanced
|
7 |
+
Qwen2.5-72B-Instruct,66.72,73.38,59.0,67.78,Instruction-tuned
|
8 |
+
Qwen2.5-72B-Instruct-Math,65.69,69.74,42.0,83.33,Reasoning-enhanced
|
9 |
+
DeepSeek-R1-Distill-Llama-70B,68.8,66.73,53.0,86.67,Reasoning-enhanced
|
10 |
+
Llama3-70B-Instruct,52.2,58.92,41.0,56.67,Instruction-tuned
|
11 |
+
Llama3.1-70B-Instruct,58.17,63.18,48.0,63.33,Instruction-tuned
|
12 |
+
Llama3.3-70B-Instruct,64.05,68.15,54.0,70.0,Instruction-tuned
|
13 |
+
DeepSeek-R1-Distill-Qwen-32B,68.97,65.48,55.0,84.44,Reasoning-enhanced
|
14 |
+
DeepSeek-R1-Distill-Qwen-14B,63.9,63.27,44.0,84.44,Reasoning-enhanced
|
15 |
+
DeepSeek-R1-Distill-Llama-8B,53.36,45.96,33.0,81.11,Reasoning-enhanced
|
16 |
+
Llama3-8B-Instruct,39.95,41.97,29.0,48.89,Instruction-tuned
|
17 |
+
Llama3.1-8B-Instruct,50.12,54.13,34.0,62.22,Instruction-tuned
|
18 |
+
Fino1-8B,61.03,60.87,40.0,82.22,Reasoning-enhanced
|