List your company

Mathematical Reasoning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
97.1Accuracy
Mathematical Reasoning on GSM8K performance trend
1,424
Jul 1, 2026
95.63Accuracy
Mathematical Reasoning on MATH performance trend
882
Apr 14, 2026
98.8Accuracy
Mathematical Reasoning on GSM8K (test) performance trend
816
May 8, 2026
99.1Accuracy (Acc)
Mathematical Reasoning on MATH 500 (Acc, SL, SE) performance trend
600
Jun 19, 2026
94.2Accuracy
Mathematical Reasoning on MATH (Accuracy) performance trend
535
Feb 26, 2026
93.3Accuracy
Mathematical Reasoning on AIME 2024 (AIME24, Math Avg) performance trend
525
Jun 19, 2026
94.13Overall Accuracy
Mathematical Reasoning on MATH (test) performance trend
433
Feb 26, 2026
79.3Accuracy
Mathematical Reasoning on AIME 2024 (Accuracy and Token Usage) performance trend
394
Jun 24, 2026
89.2Accuracy
Mathematical Reasoning on MathVista (Accuracy) performance trend
382
May 22, 2026
93.3Accuracy
Mathematical Reasoning on AIME 24 (Accuracy, Tokens) performance trend
358
Jun 18, 2026
96.7Accuracy
Mathematical Reasoning on AIME 2025 (Accuracy and Average Tokens) performance trend
353
Jun 16, 2026