Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.3Accuracy
11
Feb 26, 2026
95.7Accuracy
11
Feb 26, 2026
97.5Accuracy
11
Feb 26, 2026
75.7Pass@1 Accuracy
11
Jun 12, 2026
0.513CoT NLL
11
Feb 26, 2026
0.62Mean@4 Accuracy
11
Feb 26, 2026
82.65Mean@4
11
Feb 26, 2026
93.61Mean@4
11
Feb 26, 2026
0.815Accuracy
11
Feb 26, 2026
76.12Accuracy
11
Feb 26, 2026
79.68Accuracy
10
Jul 7, 2026
40.6Accuracy
10
Jul 7, 2026
3.37Coherence
10
Jul 2, 2026
13Pass@1
10
Jun 30, 2026
26.6Pass@1 Rate
10
Jun 30, 2026
22.079Overall Accuracy
10
Jun 29, 2026
36.7Accuracy (%)
10
Jun 23, 2026
29.86Mean@32 Accuracy
10
Jun 17, 2026
46.9EMA
10
Jun 16, 2026
88.4Accuracy
10
Jun 15, 2026
32.35Pass@1 Accuracy
10
Jun 12, 2026
76.5MMLU-Pro
10
Jun 11, 2026
18.3Pass@1
10
Jun 11, 2026
19.6Pass@1
10
Jun 11, 2026
61Pass@1
10
Jun 11, 2026