Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
998Throughput (token/s)
8
May 12, 2026
9.61Pass Rate @8
8
May 11, 2026
96.4Pass@1
8
May 11, 2026
58.8Average Score @ 32
8
May 11, 2026
63.3Avg@32 Score
8
May 11, 2026
66.5Pass@1
8
May 7, 2026
100Pass@1
8
May 7, 2026
78.8Accuracy
8
Apr 29, 2026
57Average ID Score
8
Apr 28, 2026
91.4T (Success Rate)
8
Apr 28, 2026
95.5Accuracy
8
Apr 24, 2026
63.8Accuracy
8
Apr 21, 2026
52.03Average Accuracy
8
Apr 21, 2026
56.97Acc
8
Apr 16, 2026
53.54Accuracy
8
Apr 16, 2026
38.97Accuracy (Acc)
8
Apr 16, 2026
64.7Accuracy
8
Apr 14, 2026
81.2Accuracy
8
Apr 14, 2026
49.3Pass@1
8
Apr 13, 2026
36.7Accuracy
8
Apr 7, 2026
82.6Accuracy
8
Apr 7, 2026
32.3Accuracy @1
8
Apr 3, 2026
72.5Accuracy (%)
8
Apr 2, 2026
34.69Accuracy
8
Mar 27, 2026
56.7Pass@32
8
Mar 26, 2026