Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90.7L1 Score
21
May 20, 2026
40Pass@8
21
May 20, 2026
50Pass@8
21
May 20, 2026
70.8Accuracy
21
May 19, 2026
96.9Accuracy
21
May 19, 2026
95.2Accuracy
21
May 19, 2026
96.3Accuracy
21
May 19, 2026
67.4Pass@1 Rate
21
May 20, 2026
18.3Accuracy (mean@4)
21
May 12, 2026
93.9Accuracy (mean@4)
21
May 12, 2026
78.2Accuracy (mean@4)
21
May 12, 2026
38.4Flexibility (%)
21
May 12, 2026
58Pass@1
21
May 8, 2026
54.25Accuracy
21
May 8, 2026
1.02Utility Ratio (UR)
21
Apr 30, 2026
45.3Pass@1
21
Apr 21, 2026
52.58Pass@1
21
Apr 21, 2026
34.06Pass@1
21
Apr 21, 2026
90.28Pass@1
21
Apr 21, 2026
99.3Accuracy
21
May 18, 2026
4.09CR
21
Apr 15, 2026
93.6Accuracy
21
Apr 8, 2026
73.3Accuracy
21
Apr 8, 2026
95.68AUC (%)
21
Mar 27, 2026
78.09Accuracy
21
Mar 18, 2026