Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Scientific Discovery on AIME Agent

37.78Step 1 Mean

COAT

33.15234.353535.55536.7565Mar 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
37.7843.3337.7843.3337.7843.3338.8943.33
2026.03
34.4436.6735.5636.6736.674036.6740
2026.03
33.3333.3334.4436.6734.4436.6734.4436.67
2026.03
33.3336.6738.894038.894038.8940