Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.8AIME24 Accuracy
5
Mar 11, 2026
17.6Latency (MATH)
5
Mar 5, 2026
1,168.9AUTC
5
Mar 5, 2026
54.71Mean@16
5
Mar 4, 2026
30.42Mean@16
5
Mar 4, 2026
52.4PASS@1
5
Mar 4, 2026
16.27Fine-tuning Accuracy (FA)
5
Mar 4, 2026
62.6Accuracy Pass@1
5
Mar 4, 2026
86.6Accuracy (SVAMP)
5
Feb 27, 2026
1.52Avg Rank
5
Feb 26, 2026
1.45Avg Rank
5
Feb 26, 2026
1.41Average Rank
5
Feb 26, 2026
1.4Avg Rank
5
Feb 26, 2026
1.27Average Rank
5
Feb 26, 2026
1.83Average Rank
5
Feb 26, 2026
1.77Average Rank
5
Feb 26, 2026
51.7TPS
5
Jun 2, 2026
71KL Div (alpha=1)
5
Feb 26, 2026
51.95Score
5
Feb 26, 2026
74.7Pass@1
5
Feb 26, 2026
93.37Accuracy
5
Feb 26, 2026
30.1Accuracy
5
Feb 26, 2026
96.5Accuracy
5
Feb 26, 2026
71Final Answer Accuracy
5
Feb 26, 2026
97.3Final Answer Accuracy
5
Feb 26, 2026