GuanyuH commited on
Commit
e0a4442
·
verified ·
1 Parent(s): 0014788

Upload macro_task_strict.csv

Browse files
Files changed (1) hide show
  1. macro_task_strict.csv +12 -12
macro_task_strict.csv CHANGED
@@ -1,13 +1,13 @@
1
  model,grader,n_tasks,correct,all_pass,G1,G2,G3,G4,overall_pooled
2
- anthropic/claude-opus-4.8,anthropic/claude-opus-4.8,179,0.81,0.263,0.93,0.942,0.791,0.341,0.927
3
- anthropic/claude-sonnet-5,anthropic/claude-opus-4.8,179,0.804,0.279,0.93,0.919,0.814,0.408,0.935
4
- openai/gpt-5.6-sol,anthropic/claude-opus-4.8,179,0.76,0.14,0.785,0.913,0.797,0.201,0.896
5
- anthropic/claude-sonnet-5,google/gemini-3.1-pro-preview,179,0.726,0.168,0.797,0.913,0.826,0.246,0.911
6
- openai/gpt-5.6-terra,anthropic/claude-opus-4.8,179,0.715,0.117,0.767,0.919,0.75,0.173,0.894
7
- anthropic/claude-opus-4.8,google/gemini-3.1-pro-preview,179,0.709,0.112,0.82,0.913,0.791,0.156,0.902
8
- google/gemini-3.5-flash,anthropic/claude-opus-4.8,179,0.704,0.05,0.698,0.901,0.733,0.089,0.864
9
- openai/gpt-5.6-sol,google/gemini-3.1-pro-preview,179,0.687,0.056,0.36,0.831,0.703,0.106,0.856
10
- google/gemini-3.1-pro-preview,anthropic/claude-opus-4.8,179,0.654,0.011,0.715,0.866,0.68,0.034,0.841
11
- openai/gpt-5.6-terra,google/gemini-3.1-pro-preview,179,0.603,0.061,0.424,0.855,0.715,0.101,0.859
12
- google/gemini-3.5-flash,google/gemini-3.1-pro-preview,179,0.559,0.017,0.331,0.82,0.686,0.034,0.815
13
- google/gemini-3.1-pro-preview,google/gemini-3.1-pro-preview,179,0.469,0.0,0.273,0.802,0.628,0.011,0.79
 
1
  model,grader,n_tasks,correct,all_pass,G1,G2,G3,G4,overall_pooled
2
+ anthropic/claude-opus-4.8,anthropic/claude-opus-4.8,179,0.866,0.296,0.916,0.966,0.816,0.374,0.959
3
+ anthropic/claude-sonnet-5,anthropic/claude-opus-4.8,179,0.86,0.318,0.927,0.939,0.821,0.436,0.966
4
+ openai/gpt-5.6-sol,anthropic/claude-opus-4.8,179,0.804,0.162,0.754,0.933,0.804,0.24,0.932
5
+ anthropic/claude-sonnet-5,google/gemini-3.1-pro-preview,179,0.799,0.184,0.782,0.933,0.827,0.263,0.948
6
+ anthropic/claude-opus-4.8,google/gemini-3.1-pro-preview,179,0.793,0.134,0.827,0.922,0.799,0.168,0.94
7
+ openai/gpt-5.6-terra,anthropic/claude-opus-4.8,179,0.782,0.145,0.749,0.939,0.771,0.212,0.928
8
+ openai/gpt-5.6-sol,google/gemini-3.1-pro-preview,179,0.765,0.073,0.369,0.86,0.743,0.134,0.897
9
+ google/gemini-3.5-flash,anthropic/claude-opus-4.8,179,0.743,0.056,0.693,0.939,0.754,0.101,0.897
10
+ google/gemini-3.1-pro-preview,anthropic/claude-opus-4.8,179,0.698,0.006,0.67,0.899,0.709,0.039,0.877
11
+ openai/gpt-5.6-terra,google/gemini-3.1-pro-preview,179,0.682,0.078,0.441,0.877,0.721,0.134,0.897
12
+ google/gemini-3.5-flash,google/gemini-3.1-pro-preview,179,0.626,0.017,0.324,0.855,0.693,0.039,0.851
13
+ google/gemini-3.1-pro-preview,google/gemini-3.1-pro-preview,179,0.508,0.0,0.257,0.821,0.637,0.011,0.826