Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.3Mean@16
3
May 28, 2026
89Mean@16 Accuracy
3
May 28, 2026
93.86Accuracy
3
May 28, 2026
25.6Accuracy (Swahili)
3
May 28, 2026
35.2Accuracy (Swahili)
3
May 28, 2026
87.2Accuracy (Swahili)
3
May 28, 2026
38.89EM (Strict)
3
May 27, 2026
0.531Score
3
May 27, 2026
47.33Score
3
May 27, 2026
10Accuracy
3
May 25, 2026
61.78Teacher Accuracy
3
May 22, 2026
87.22Teacher Accuracy
3
May 22, 2026
0.3Risk
3
May 21, 2026
99Accuracy
3
May 20, 2026
66.7Pass@512
3
May 19, 2026
71.7Pass@512
3
May 19, 2026
51DRS Score
3
May 18, 2026
138Throughput (tok/s)
3
May 15, 2026
95.38Accuracy (mean)
3
May 15, 2026
93.42Mean Accuracy
3
May 15, 2026
37.38Accuracy (Ckpt 1)
3
May 13, 2026
89.16Accuracy
3
May 13, 2026
24.38AIME 25 Accuracy
3
May 12, 2026
6.5Total Tokens Processed
3
May 12, 2026
58.5Performance
3
May 12, 2026