Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.1Accuracy
1,424
Jul 1, 2026
99Accuracy
954
May 28, 2026
60.9Accuracy
922
Jul 8, 2026
95.63Accuracy
882
Apr 14, 2026
98.8Accuracy
816
May 8, 2026
99.1Accuracy (Acc)
600
Jun 19, 2026
99.1Accuracy
589
Jun 26, 2026
229.2Score
566
Jun 19, 2026
94.2Accuracy
535
Feb 26, 2026
93.3Accuracy
525
Jun 19, 2026
98Accuracy
499
Mar 25, 2026
96.4Top-1 Accuracy
452
Jun 23, 2026
98.4Accuracy
442
Mar 25, 2026
94.13Overall Accuracy
433
Feb 26, 2026
97Accuracy
403
Apr 14, 2026
79.3Accuracy
394
Jun 24, 2026
100Accuracy
388
May 19, 2026
89.2Accuracy
382
May 22, 2026
99.2Accuracy
378
Jun 24, 2026
95.18Accuracy (%)
375
Jun 4, 2026
94Accuracy
370
Mar 25, 2026
93.3Accuracy
358
Jun 18, 2026
97.8Accuracy (GSM8K)
358
Feb 26, 2026
98.84Accuracy
354
May 25, 2026
96.7Accuracy
353
Jun 16, 2026