Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
63.28Accuracy
6
May 26, 2026
3.9Gain Score
6
May 21, 2026
8.78Gain Score
6
May 21, 2026
60Pass@8
6
May 20, 2026
60Pass@8
6
May 20, 2026
90Acc
6
May 20, 2026
78.4Accuracy
6
May 20, 2026
96Accuracy
6
May 20, 2026
88.1Accuracy
6
May 20, 2026
79.8Average Accuracy
6
May 19, 2026
86.8Pass@1
6
May 19, 2026
53.3Pass@1
6
May 19, 2026
93.9Pass@1
6
May 19, 2026
23.3Pass@1
6
May 19, 2026
1.741Decode Speed (tokens/s)
6
May 19, 2026
94.14Accuracy (%)
6
May 19, 2026
26.65Accuracy
6
May 18, 2026
83.3Accuracy
6
May 15, 2026
59.8AMO-Bench Accuracy
6
May 14, 2026
46Accuracy
6
May 14, 2026
34.2AIME 2024 Score
6
May 14, 2026
15.6Accuracy
6
May 14, 2026
64Accuracy
6
May 13, 2026
64Accuracy
6
May 13, 2026
91.85Accuracy
6
May 13, 2026