Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.8Pass@1
2
Jun 8, 2026
90.8Pass@1
2
Jun 8, 2026
0.968Pass@1
2
Jun 8, 2026
5Positive Seeds
2
Jun 8, 2026
5Positive Seeds Count
2
Jun 8, 2026
29.94Accuracy
2
Jun 4, 2026
68.99Accuracy
2
Jun 4, 2026
31.7E*S
2
Jun 4, 2026
76.3Score
2
Jun 4, 2026
47.8Accuracy
2
Jun 2, 2026
58Accuracy
2
Jun 1, 2026
39.8Macro Accuracy
2
Jun 1, 2026
43.7Error Rate
2
May 28, 2026
47.2Error Rate
2
May 28, 2026
18.14EM (strict)
2
May 27, 2026
50Accuracy
2
May 27, 2026
1.59Accuracy
2
May 27, 2026
66.2Score
2
May 26, 2026
78.4Initial Accuracy
2
May 26, 2026
76.4Accuracy (n=1k) on GSM8K
2
May 26, 2026
2Turn 1 Score
2
May 26, 2026
6.7Turn 1 Score
2
May 26, 2026
6.7Turn 1 Score
2
May 26, 2026
62.5P@1
2
May 22, 2026
66.8Accuracy
2
May 21, 2026