Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95.7Pass@4 Rate
14
Apr 3, 2026
87.31pass@4
14
Apr 3, 2026
27.03Pass@2
14
Mar 31, 2026
19.5Pass@2
14
Mar 31, 2026
63.4Pass@2
14
Mar 31, 2026
16.88Accuracy
14
Mar 31, 2026
24.58Accuracy (AIME 24)
14
Mar 31, 2026
17.66Accuracy
14
Mar 31, 2026
82.73MATH500 Score
14
Mar 19, 2026
63.6Accuracy
14
Mar 17, 2026
59.2Accuracy (Amharic)
14
Mar 9, 2026
85.56Accuracy
14
Mar 5, 2026
71.3Accuracy
14
Mar 4, 2026
56.4Overall Performance
14
Feb 27, 2026
90.2Accuracy (Vary Both)
14
Feb 26, 2026
83.33Accuracy
14
Feb 26, 2026
58Avg@32
14
Feb 26, 2026
39.4Average Score @32
14
Feb 26, 2026
86Avg@32
14
Feb 26, 2026
91.4Average Score @32
14
Feb 26, 2026
42.9Avg@32
14
Feb 26, 2026
58.8pass@1
14
Feb 26, 2026
26Pass@1
14
Feb 26, 2026
85.7Pass@1
14
Feb 26, 2026
92.35Accuracy
14
Feb 26, 2026