Healthcare.pdf / macro_task_strict.csv
GuanyuH's picture
Upload macro_task_strict.csv
e0a4442 verified
Raw History Blame Contribute Delete
1.24 kB
model,grader,n_tasks,correct,all_pass,G1,G2,G3,G4,overall_pooled
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
anthropic/claude-sonnet-5,anthropic/claude-opus-4.8,179,0.86,0.318,0.927,0.939,0.821,0.436,0.966
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
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
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
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
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
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
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
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
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
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