Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
38.6Pass@1
14
Apr 27, 2026
83.9Accuracy
14
Apr 21, 2026
87.4Accuracy
14
Apr 21, 2026
90.8Accuracy
14
Apr 21, 2026
96.1Accuracy
14
Apr 21, 2026
90.4Pass@1 Rate
14
Apr 20, 2026
75.6Pass@1
14
Apr 20, 2026
89.99Accuracy (GSM8K)
14
Apr 15, 2026
94Average Score @8
14
Apr 15, 2026
62.9Avg@8
14
Apr 15, 2026
16Avg@8 Score
14
Apr 15, 2026
94.3Pass@1 Accuracy
14
May 7, 2026
82.3ARC-c (pass@1)
14
Apr 13, 2026
36AIME 24 Pass@32
14
Apr 13, 2026
26.67Result Accuracy
14
Apr 13, 2026
91.66Accuracy
14
Apr 13, 2026
79.6Accuracy
14
Apr 9, 2026
85.7Accuracy
14
Apr 9, 2026
3.903Speedup Ratio
14
Apr 8, 2026
1Relative Cost
14
Apr 8, 2026
1Relative Cost
14
Apr 8, 2026
1Relative Cost
14
Apr 8, 2026
95.68Accuracy
14
Apr 8, 2026
71.88Pass@4 Score
14
Apr 3, 2026
44.84pass@4
14
Apr 3, 2026