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

Mathematical Reasoning on OlympiadBench (test)

51.8@1 Success Rate

LUFFY

20.91228.93136.9544.969Jan 25, 2026Feb 1, 2026Feb 9, 2026Feb 16, 2026Feb 24, 2026Mar 3, 2026Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
51.8----
2026.03
51.4----
2026.03
50----
2026.03
49.2----
2026.03
48.6----
2026.03
43.2----
2026.01
32.841.844.939.57
2026.01
32.540.843.838.88.5
2026.01
31.8363835.18.6
2026.01
31.53941.837.28.4
2026.01
30.131.832.531.58.5
2026.03
30----
2026.01
29.13739.534.87.5
2026.01
27.434.536.832.66
2026.01
22.130.232.627.92.6