Knowledge Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
91.43Accuracy
148
Jun 5, 2026
92.16MMLU Knowledge Reasoning Accuracy
73
May 20, 2026
91.9Accuracy
48
Jun 16, 2026
67.3Accuracy
48
Jun 5, 2026
89.6MATH Accuracy
24
Jun 2, 2026
41.5Accuracy
22
May 29, 2026
43Accuracy
22
May 29, 2026
75.4Accuracy (avg@8)
16
May 8, 2026
4.45Accuracy
12
Jun 23, 2026
90.1Accuracy
8
Feb 26, 2026
82.8pass@1
7
Feb 26, 2026
51Accuracy
6
May 21, 2026
74.3Accuracy
6
Feb 26, 2026
89.9Pass@1
6
Feb 26, 2026
63Accuracy
5
May 27, 2026
68.5EM
5
Feb 26, 2026
68.6Accuracy
4
May 27, 2026
29.87Normalized Accuracy
3
Apr 23, 2026
35.41Normalized Accuracy
3
Apr 23, 2026
32Normalized Accuracy
3
Apr 23, 2026
36.08Accuracy (Normalized)
3
Apr 23, 2026
37.3Score
3
Feb 26, 2026
99Quality
2
Jun 26, 2026