Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.1SR (%)
14
May 26, 2026
68.5SR
14
May 26, 2026
28.2Pass@1 Rate
14
May 21, 2026
88.2Accuracy (pass@1)
14
May 21, 2026
96.4Accuracy (MATH-500)
14
May 19, 2026
94.4Accuracy (%)
14
May 19, 2026
48.9Pass@1
14
May 18, 2026
5.8pass@1
14
May 18, 2026
54.3Average Score (avg@8)
14
May 18, 2026
94.9Avg@64
14
May 18, 2026
50.3Avg@64
14
May 18, 2026
61.7Average Score (avg@64)
14
May 18, 2026
36.67ACC
14
May 13, 2026
56.67Accuracy (ACC)
14
May 13, 2026
93Accuracy (ACC)
14
May 13, 2026
92Accuracy (ACC)
14
May 13, 2026
451.8Throughput (H200 TPS)
14
May 12, 2026
48.7Accuracy
14
May 12, 2026
9Pass@1
14
May 26, 2026
60.9Mean@32 Accuracy
14
May 12, 2026
36.5Mean@32 Accuracy
14
May 12, 2026
66Mean@32 Accuracy
14
May 12, 2026
75.2Mean@32 Accuracy
14
May 12, 2026
16.7Accuracy
14
May 8, 2026
0.001Execution Cost
14
May 12, 2026