Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.1FR slc&acc
8
Jul 2, 2026
35.1FR SLC & Acc
8
Jul 2, 2026
2.62Speedup
8
Jun 26, 2026
42.8pass@1
8
May 26, 2026
8.1Pass@1
8
May 26, 2026
30.4Pass@1
8
May 26, 2026
40.3pass@1
8
May 22, 2026
84.9Pass@1 Accuracy
8
May 22, 2026
43.1Accuracy
8
Feb 26, 2026
97.86Accuracy
8
Feb 26, 2026
78.33Kazakh (Cyrl) Accuracy
7
May 21, 2026
0.87AUROC
7
May 1, 2026
0.42Occ Score
7
May 1, 2026
30.31Accuracy (AQuA)
7
Apr 28, 2026
59.2Pass@1
7
Apr 15, 2026
69.9Pass@1
7
Apr 15, 2026
66Accuracy
7
Apr 13, 2026
83.2Accuracy (GSM CoT)
7
Apr 13, 2026
64.5Algebra Score
7
Feb 27, 2026
95.8GSM8K Accuracy
7
Feb 26, 2026
79.9Accuracy
6
Jul 3, 2026
20.31Avg@32
6
Jun 9, 2026
20.21Avg@32
6
Jun 9, 2026
38.44Avg Score @32
6
Jun 9, 2026
41.35Average Score @32
6
Jun 9, 2026