Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.5Pass@1
32
Jun 25, 2026
99.2ASR
32
Apr 28, 2026
86Pass@1 Accuracy
32
Apr 21, 2026
70Accuracy (ACC)
32
Apr 30, 2026
15.1MATH Score
32
Apr 16, 2026
55.8Pass@1
32
Apr 15, 2026
78.3pass@1
32
Apr 15, 2026
76.9Accuracy (%)
32
Mar 17, 2026
94.98Accuracy
32
Mar 4, 2026
86.3Accuracy
32
May 26, 2026
92Avg@5 Score
32
Feb 26, 2026
94Avg@5 Score
32
Feb 26, 2026
97.1Avg@5 Success Rate
32
Feb 26, 2026
76.6Avg@5
32
Feb 26, 2026
39.7pass@1
32
Mar 4, 2026
72Pass@1
32
May 7, 2026
47.36Score
32
Apr 23, 2026
90Accuracy
32
Feb 26, 2026
68.2Accuracy
32
Feb 26, 2026
41.7Pass@1 (Avg@16)
32
Feb 26, 2026
45.4Accuracy
32
Feb 26, 2026
82.56Accuracy
32
Feb 26, 2026
94GSM8K Accuracy
32
Feb 26, 2026
94.16Accuracy
32
Feb 26, 2026
38.2Accuracy
31
Jun 12, 2026