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

Mathematical Reasoning on Olympiad Bench (Avg@32)

41.25Avg@32

LAD

39.398839.879440.3640.8406Feb 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
41.25
2026.02
41.16
2026.02
40.8
2026.02
40.3
2026.02
40.13
2026.02
39.47