Mathematical Reasoning on AIME 24 (Pass@1, #Tok)
86.7Pass@1 Accuracy
DyCon
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 86.7 | 18,867 | |
2026.06 | 83.3 | 21,493 | |
2026.06 | 83.3 | 18,652 | |
2026.06 | 76.7 | 12,746 | |
2026.06 | 76.7 | 7,619 | |
2026.06 | 76.7 | 10,181 | |
2026.06 | 76.7 | 10,536 | |
2026.06 | 73.3 | 16,556 | |
2026.06 | 73.3 | 13,364 | |
2026.06 | 73.3 | 9,405 | |
2026.06 | 73.3 | 12,794 | |
2026.06 | 73.3 | 10,369 | |
2026.06 | 70 | 10,087 | |
2026.06 | 66.7 | 12,728 | |
2026.06 | 66.7 | 11,507 | |
2026.06 | 63.3 | 11,029 | |
2026.06 | 63.3 | 12,064 | |
2026.06 | 63.3 | 11,426 | |
2026.06 | 60 | 10,034 | |
2026.06 | 56.7 | 8,345 | |
2026.06 | 53.3 | 11,419 | |
2026.06 | 53.3 | 8,457 | |
2026.06 | 53.3 | 10,906 | |
2026.06 | 53.3 | 12,393 | |
2026.06 | 50 | 13,008 | |
2026.06 | 50 | 12,588 | |
2026.06 | 49.2 | 9,839 | |
2026.06 | 43.3 | 11,092 | |
2026.06 | 43.3 | 7,913 | |
2026.06 | 40 | 7,281 | |
2026.06 | 30 | 5,123 | |
2026.06 | 26.7 | 7,841 | |
2026.06 | 16.7 | 4,222 | |
2026.06 | 13.3 | 1,229 |