Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
38.4Pass@k
24
May 13, 2026
73.1Pass@k
24
May 13, 2026
46.78Avg@k
24
May 13, 2026
39.94Avg@k
24
May 13, 2026
62.19Avg@k
24
May 13, 2026
2.91Speedup
24
May 12, 2026
48.9Accuracy
24
May 12, 2026
63Accuracy
24
May 12, 2026
62.8Accuracy
24
May 11, 2026
85.8Accuracy
24
May 11, 2026
78.5Accuracy
24
May 11, 2026
71.74Accuracy
24
May 11, 2026
5.7Avg Forward Passes
24
May 8, 2026
7.3Average Forward Passes
24
May 8, 2026
6Avg Forward Passes
24
May 8, 2026
53.8NFE (4-shot)
24
Jun 4, 2026
639.7Throughput (Token/s)
24
Apr 23, 2026
17.1Accuracy
24
Apr 21, 2026
15.4Accuracy
24
Apr 21, 2026
16.2Accuracy
24
Apr 21, 2026
22.9Accuracy
24
Apr 21, 2026
78.2Accuracy
24
Apr 21, 2026
95.2Accuracy
24
Apr 21, 2026
81Accuracy
24
Apr 21, 2026
76.7Accuracy
24
Apr 21, 2026