Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.94Accuracy
4
Mar 6, 2026
0.051Brier Score
4
Mar 5, 2026
49.31Mean@16
4
Mar 12, 2026
64.31Mean@16
4
Mar 4, 2026
62.35Mean@16
4
Mar 4, 2026
47.06Mean@16
4
Mar 4, 2026
30.42Mean@16
4
Mar 4, 2026
43.12Mean@16
4
Mar 4, 2026
1,896.9MTL Score
4
Mar 4, 2026
39.2R-PSR
4
Mar 4, 2026
39Accuracy
4
Mar 4, 2026
92.4Accuracy
4
Mar 4, 2026
95Accuracy
4
Feb 26, 2026
94Accuracy
4
Feb 26, 2026
57.1GSM8K Score
4
Feb 26, 2026
9.55Throughput (tokens/s)
4
Feb 26, 2026
8.58Throughput (tokens/s)
4
Feb 26, 2026
930Avg Generated Tokens
4
Feb 26, 2026
2.34Training Cost (USD)
4
Feb 26, 2026
59.7Mean Accuracy @16
4
Feb 26, 2026
13.5Mean@16
4
Feb 26, 2026
97.8ANLL
4
Feb 26, 2026
25.62Pass@1
4
Feb 26, 2026
89.9Algebra222 Accuracy
4
Feb 26, 2026
81.7GSM8K Score
4
Feb 26, 2026