Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
41.46Accuracy
18
Mar 4, 2026
57.51Accuracy
18
Mar 4, 2026
91.87Accuracy
18
Feb 26, 2026
82.15Average Accuracy
18
Feb 26, 2026
65.4Accuracy
17
May 14, 2026
14.71AVGLEN
17
Apr 15, 2026
6.04IA Score
17
Mar 13, 2026
97.6Accuracy (SAT)
17
Mar 10, 2026
73.9Accuracy
17
May 19, 2026
38.4Pass@1
17
Mar 12, 2026
68COPA
17
Feb 26, 2026
85Pass@1
17
Feb 26, 2026
65.83Accuracy (Simple)
16
Jun 4, 2026
67.17Pass@4 Accuracy
16
Jun 2, 2026
97.9Pass@4
16
May 28, 2026
74.3Pass@4
16
May 28, 2026
89.4Pass@4
16
May 28, 2026
75.7Pass@4
16
May 28, 2026
50.2Accuracy
16
May 26, 2026
97.32Accuracy
16
Jun 26, 2026
64.5Exact Match (EM)
16
May 12, 2026
93.5Flexible Extract
16
May 11, 2026
95.1Exact Match Accuracy
16
May 11, 2026
93.6Accuracy
16
Apr 23, 2026
77.46Avg@k
16
Apr 20, 2026