Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88.87AUROC
14
Feb 26, 2026
62.75Pass@1
14
Feb 26, 2026
18.03Pass@1
14
Feb 26, 2026
70.38Pass@1
14
Feb 26, 2026
94.58Pass@1
14
Feb 26, 2026
93.54Pass@1
14
Feb 26, 2026
84.64Accuracy
14
Feb 26, 2026
95Acc
14
Feb 26, 2026
65Accuracy
14
Feb 26, 2026
95.1Rel Score
13
May 29, 2026
45.2BBH Score
13
May 27, 2026
55.9Accuracy (Reasoning on MMMU-Pro)
13
May 29, 2026
51Accuracy
13
May 19, 2026
46.95Accuracy
13
May 15, 2026
72Avg@8
13
Apr 28, 2026
14.8Pass@1
13
Apr 10, 2026
7.28Judge Score
13
Apr 10, 2026
98.5Accuracy
13
Mar 27, 2026
81Pass@1 Score
13
May 26, 2026
52.4MMMU Score
13
Feb 26, 2026
72.9MMSU Accuracy (Audio)
13
Feb 26, 2026
66.02Accuracy
13
Feb 26, 2026
83.4Accuracy
12
Jun 16, 2026
100Math Score
12
Jun 5, 2026
55.7Pass@1
12
Jun 4, 2026