Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
52.1Accuracy
27
Jun 9, 2026
45Pass@1 Absolute
26
Jul 7, 2026
43Pass@1
26
Jul 7, 2026
31Pass@1
26
Jul 7, 2026
71.87Accuracy
26
Jun 18, 2026
74Accuracy (Avg@8)
26
Jul 7, 2026
50Performance (%)
26
Jun 24, 2026
3.88Speed (×)
26
May 26, 2026
94.2Accuracy
26
Jun 30, 2026
76.49Average Score
26
Jul 7, 2026
68.9Score
26
May 26, 2026
86.6Accuracy
26
May 12, 2026
95.6Accuracy
26
May 26, 2026
55.4Pass@1
26
Jun 30, 2026
73.6Pass@1
26
Jun 9, 2026
95.3Accuracy
26
Apr 7, 2026
67.5AIME24 Avg@16
26
May 12, 2026
79.9Accuracy
26
Apr 14, 2026
87.18Accuracy
26
Jun 16, 2026
89.79Accuracy
26
May 13, 2026
73.78Accuracy (avg@4)
26
Apr 3, 2026
68.75AIME24 Score
26
Feb 26, 2026
52.3Mean Accuracy
26
Apr 14, 2026
6.57ACC
26
Feb 27, 2026
2.7Latency (s)
26
Mar 5, 2026