Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67Pass@1
15
Jun 23, 2026
13.3Pass@1
15
Jun 23, 2026
10Pass@1
15
Jun 23, 2026
5P@1
15
Jun 19, 2026
10.83P@1
15
Jun 19, 2026
8.05Pass@1
15
Jun 19, 2026
86.68P@1
15
Jun 19, 2026
82.25Pass@1
15
Jun 19, 2026
13,040Thinking Tokens
15
Jun 17, 2026
10,163Thinking Tokens
15
Jun 17, 2026
63.5Pass@1
15
Jun 2, 2026
90Pass@1 Accuracy
15
Jun 2, 2026
92Pass@1
15
Jun 2, 2026
78.8Pass@1
15
Jun 2, 2026
30Pass@1
15
Jun 2, 2026
30Pass@1 Accuracy
15
Jun 2, 2026
1,828.7Throughput (tokens/s)
15
Jun 2, 2026
89.05Accuracy (Avg@8)
15
Jul 7, 2026
35Average@8 Score
15
May 29, 2026
51.7Accuracy (ar)
15
May 28, 2026
83.3Accuracy
15
May 26, 2026
57.88ThmQA Score
15
May 26, 2026
54.11Accuracy
15
May 19, 2026
70.9Average@16 Accuracy
15
May 19, 2026
47.8Average@16 Accuracy
15
May 19, 2026