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

Mathematical Reasoning on AIME 24 (Avg@32 Accuracy)

93.85Avg@32 Accuracy

FlashMLA

17.87837.601557.32577.0485Feb 2, 2026Feb 3, 2026Feb 5, 2026Feb 6, 2026Feb 8, 2026Feb 9, 2026Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
93.85
2026.02
93.65
2026.02
91.87
2026.02
91.67
2026.02
52.8
2026.02
51.8
2026.02
51
2026.02
50.9
2026.02
50.8
2026.02
49.8
2026.02
38.8
2026.02
37.29
2026.02
35.31
2026.02
34.7
2026.02
34.2
2026.02
34
2026.02
33.8
2026.02
33.13
2026.02
32.4
2026.02
31.5
2026.02
31.35
2026.02
28.96
2026.02
20.8