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

Mathematical Reasoning on AIME 25 (Avg@32, #Token)

32.8Avg@32 Score

GR³

16.26420.55724.8529.143Mar 11, 2026Mar 18, 2026Mar 26, 2026Apr 3, 2026Apr 10, 2026Apr 18, 2026Apr 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
32.88,137
2026.03
31.412,985
2026.04
29.8-
2026.04
28.2-
2026.03
27.83,153
2026.04
26.4-
2026.03
24.79,234
2026.03
24.15,008
2026.03
23.615,799
2026.04
23.1-
2026.04
22.9-
2026.04
21.9-
2026.04
21.6-
2026.04
21-
2026.03
20.68,275
2026.04
16.9-