Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
29.55Accuracy
8
Apr 1, 2026
4.5Overall Score
8
Mar 26, 2026
60.67Success Rate
8
Mar 20, 2026
84.33Success Rate
8
Mar 20, 2026
97Success Rate
8
Mar 20, 2026
8.33Success Rate
8
Mar 20, 2026
30.67Success Rate
8
Mar 20, 2026
81.7Normalized Log Accuracy
8
Mar 18, 2026
0.749Normalized Log Accuracy
8
Mar 18, 2026
92Normalized Log Accuracy
8
Mar 18, 2026
52.4MATH Score
8
Mar 10, 2026
37.5Accuracy (ARC EL)
8
Mar 6, 2026
51.11Accuracy
8
Mar 6, 2026
92.16Pass@1
8
Mar 4, 2026
58.8Pass@1
8
Mar 4, 2026
71.4BERTScore
8
Mar 4, 2026
48.8ROUGE-1
8
Mar 4, 2026
0.826Accuracy
8
Feb 26, 2026
1.38Accuracy Improvement
8
Feb 27, 2026
36.33RA
8
Feb 26, 2026
89.8Avg@8
7
Jun 16, 2026
95.64Avg@64
7
Jun 16, 2026
72.4MMAU Score
7
Jun 9, 2026
62.2MMSU Reasoning Score
7
Jun 9, 2026
62.44Overall Score
7
Jun 8, 2026