Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88ARC Score
11
Feb 26, 2026
88.12Solve Rate
11
Feb 26, 2026
69.58CMMLU
11
Feb 26, 2026
6.7Error Rate (ERR)
11
Feb 26, 2026
10Error Rate
11
Feb 26, 2026
0.036Error Rate
11
Feb 26, 2026
83.803Accuracy
11
Feb 26, 2026
96.8Accuracy
11
Feb 26, 2026
80.1BBH Score
10
Jul 7, 2026
56.48MuSR Score
10
Jul 7, 2026
76Accuracy
10
Jun 17, 2026
1,580Logical Consistency Score (LCS)
10
Jun 4, 2026
83.4Accuracy
10
Jun 4, 2026
87.8Accuracy
10
Jun 4, 2026
90.1Accuracy (ReClor ID)
10
Jun 4, 2026
88.7Accuracy
10
Jun 4, 2026
91.2Accuracy (ARB ID)
10
Jun 4, 2026
74Accuracy
10
May 19, 2026
71.1MMStar Reasoning Score
10
May 19, 2026
15.9Accuracy
10
May 13, 2026
26.83Accuracy
10
May 13, 2026
57Reasoning Accuracy
10
Apr 15, 2026
77.9Pass@1
10
Apr 14, 2026
46.7Average Score
10
Apr 13, 2026
0.934Accuracy
10
Mar 27, 2026