Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58.65Pass@1 Score
6
May 22, 2026
47.8MathVision Accuracy
6
May 6, 2026
54.54Pass@1
6
Apr 28, 2026
48.19Pass@1
6
Apr 28, 2026
71.69Pass@1
6
Apr 28, 2026
27.92Pass@1
6
Apr 28, 2026
39.79Pass@1
6
Apr 28, 2026
90.4AIME 2026 Avg Score
6
Mar 27, 2026
92Pass Rate
6
Mar 27, 2026
92.2Math500 Accuracy
6
Mar 27, 2026
39Pass@1
6
Mar 27, 2026
53.3Pass@1 Score
6
Mar 27, 2026
73.64Avg@32
6
Mar 24, 2026
31.15Avg@32 Score
6
Mar 24, 2026
39.06Avg@32 Score
6
Mar 24, 2026
90Avg@1 Score
6
Mar 6, 2026
24.12Avg@32
6
Mar 6, 2026
33.34Avg@32 Score
6
Mar 6, 2026
40.08Avg@32
6
Feb 26, 2026
56.45Avg@32
6
Feb 26, 2026
9.81Avg@32 Score
6
Feb 26, 2026
19.6Avg Recall@32
6
Feb 26, 2026
37.58Avg@32
6
Feb 26, 2026
41.25Avg@32
6
Feb 26, 2026
77.66Average Success Rate (Avg@32)
6
Feb 26, 2026