Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84.09Accuracy
33
Jun 16, 2026
94.02Accuracy
33
Jun 16, 2026
97.18Accuracy
33
Jun 16, 2026
72.29Accuracy
33
Jun 16, 2026
80Pass@1 Accuracy
33
Jun 8, 2026
36.5Accuracy
33
Jun 1, 2026
92.6Accuracy (MATH-500)
33
Jul 9, 2026
61.67AIME 2024 Score
33
May 19, 2026
38.2Pass@1
33
May 22, 2026
456.9Tokens Used
33
Apr 24, 2026
937.4Tokens
33
Apr 24, 2026
7.46Spd
33
Apr 3, 2026
49.79Average@16 Score
33
May 28, 2026
62.8Pass@1
33
May 8, 2026
35.44Accuracy
33
Feb 26, 2026
94.16Accuracy
33
Jun 23, 2026
67.3Pass@1
33
Feb 26, 2026
95Pass@1
33
Feb 26, 2026
56.67Accuracy
33
Feb 26, 2026
96.5Accuracy
33
Feb 26, 2026
81.8Accuracy
33
Jun 4, 2026
92.17Accuracy
32
Jun 4, 2026
94.7Accuracy (AMC 2023)
32
Jun 30, 2026
70Accuracy
32
Jun 4, 2026
3.14Speedup
32
May 11, 2026