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

Mathematical Reasoning on Olympiad (pass@1, pass@256)

42.4Pass@1

F-CISPO

18.4824.6930.937.11Feb 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
42.477.5
2026.02
41.576.9
2026.02
40.975.6
2026.02
40.571.8
2026.02
37.865.8
2026.02
37.671.9
2026.02
37.571.6
2026.02
37.276.2
2026.02
3775.5
2026.02
36.473.2
2026.02
36.474
2026.02
36.374.3
2026.02
23.261.3
2026.02
22.555.4
2026.02
21.558.7
2026.02
2148.4
2026.02
20.161.3
2026.02
19.459.3