Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.797Final Reward
3
Feb 26, 2026
23.56Pass@8
3
Feb 26, 2026
23.75Pass@1
3
Feb 26, 2026
7.5Pass@1
3
Feb 26, 2026
45.54AVG@8
3
Feb 26, 2026
0.846AVG@8 Score
3
Feb 26, 2026
0.535Accuracy
3
Feb 26, 2026
14.8Accuracy
3
Feb 26, 2026
92Accuracy
3
Feb 26, 2026
77Acc
3
Feb 26, 2026
0.691Pearson r
3
Feb 26, 2026
68.1Accuracy
3
Feb 26, 2026
48.9Accuracy
3
Feb 26, 2026
96.6Accuracy
3
Feb 26, 2026
88.2Accuracy
3
Feb 26, 2026
66.1Accuracy
3
Feb 26, 2026
72.7Accuracy
3
Feb 26, 2026
48.31Tokens/s
3
Feb 26, 2026
19.1Average Accuracy
3
Feb 26, 2026
23.5Average Accuracy
3
Feb 26, 2026
42.4Accuracy
3
Feb 26, 2026
78.67Pass@1
3
Feb 26, 2026
100Accuracy
3
Feb 26, 2026
0.854Structural Accuracy
3
Feb 26, 2026
73.94Accuracy
3
Feb 26, 2026