Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.2Pass@1
16
Feb 26, 2026
50Pass@1
16
Feb 26, 2026
56.67Pass@1
16
Feb 26, 2026
66.67Pass@1
16
Feb 26, 2026
92.3Accuracy
16
Feb 26, 2026
55Pass@1
16
Feb 26, 2026
13.86Throughput
16
Feb 26, 2026
0.56Seed (Avg@5)
16
Feb 26, 2026
76.6Seed Score
16
Feb 26, 2026
92Seed Score
16
Feb 26, 2026
94Seed
16
Feb 26, 2026
95.6Seed
16
Feb 26, 2026
55.9Multi-step pass@5 Accuracy
16
Jun 1, 2026
53.72Average Score
16
Feb 26, 2026
51.8Hit@1
16
Feb 26, 2026
82.9Hit@1 Accuracy
16
Feb 26, 2026
41.62Pass@1
16
May 29, 2026
89.11Accuracy
16
Apr 9, 2026
98.44Accuracy
16
Feb 26, 2026
71.25Accuracy
16
Feb 26, 2026
83.75Accuracy
16
Feb 26, 2026
91.6Accuracy
16
Feb 26, 2026
24.6Accuracy
16
Feb 26, 2026
78.2Accuracy (M→M-500)
16
Feb 26, 2026
91.7Accuracy (GSM8K)
16
Feb 26, 2026