Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.8Accuracy
5
Apr 28, 2026
16.1GSM8K Accuracy
5
Apr 28, 2026
69.1Initial F1
5
Apr 28, 2026
56.6Initial F1 Score
5
Apr 28, 2026
83.2VAcc (Verification Accuracy)
5
Apr 27, 2026
92.34Verification Accuracy (VAcc)
5
Apr 27, 2026
1.88Accuracy Change
5
Apr 24, 2026
73Accuracy
5
Apr 21, 2026
56.7Accuracy
5
Apr 21, 2026
10.2Accuracy Improvement Delta
5
Apr 21, 2026
5.7Accuracy Improvement (GSM8K)
5
Apr 21, 2026
56.75Acc (mean@8)
5
Apr 16, 2026
90.03Accuracy (mean@8)
5
Apr 16, 2026
59.3AIME 2024 Score
5
Apr 13, 2026
7.03TPF
5
Apr 10, 2026
5.94TPF
5
Apr 10, 2026
2.04Time Per First Token (TPF)
5
Apr 10, 2026
56Accuracy
5
Apr 10, 2026
100Accuracy
5
Apr 14, 2026
69p-hat
5
Mar 31, 2026
96.42ECR
5
Mar 31, 2026
65.19Pass@1
5
Mar 26, 2026
82.98Accuracy
5
Mar 20, 2026
91.28Accuracy
5
Mar 20, 2026
0.39Score
5
Mar 13, 2026