Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
37.08Accuracy
3
May 12, 2026
49Performance
3
May 12, 2026
13.34Pass@1 Accuracy
3
May 11, 2026
1.18Pass@1
3
May 11, 2026
87.9Pass@1
3
May 8, 2026
86.2Pass@1
3
May 8, 2026
69.9Pass@1 Accuracy
3
May 8, 2026
25Delta Accuracy (pp)
3
May 8, 2026
95.68pass@16
3
May 8, 2026
54.82Pass@16
3
May 8, 2026
90.49pass@16 Success Rate
3
May 8, 2026
12.4Accuracy
3
May 8, 2026
93.07Mean Accuracy (±STD)
3
May 8, 2026
93.83Mean Accuracy
3
May 8, 2026
54.7Accuracy
3
May 8, 2026
10.4Pass@1 Accuracy
3
May 8, 2026
30.2Mean@32
3
May 8, 2026
95.6Accuracy
3
May 7, 2026
60Average Accuracy @32
3
May 6, 2026
10Time (minutes)
3
Apr 29, 2026
79.37Deductive Accuracy
3
Apr 28, 2026
87Verification Accuracy
3
Apr 27, 2026
27.9PPL
3
Apr 23, 2026
24.8Perplexity (PPL)
3
Apr 23, 2026
49.3Success Rate (SR)
3
Apr 23, 2026