General Knowledge Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82.93Accuracy
64
May 12, 2026
75.9Accuracy
64
Apr 20, 2026
95.7Accuracy
36
Apr 8, 2026
75.41Accuracy (MMLU-Pro)
27
Apr 14, 2026
80.515-shot Accuracy
25
Jul 7, 2026
73.12Accuracy (MMLU College GK Reasoning)
20
Jul 7, 2026
67.2Accuracy
20
Jul 7, 2026
50Score
17
Jun 23, 2026
68.21Avg@k
15
May 13, 2026
75.6Accuracy
15
Apr 29, 2026
54.6Accuracy
10
Jul 8, 2026
37.72Accuracy
10
Feb 26, 2026
91.6BCA
9
May 13, 2026
9.3Best-of-16 Delta
6
Apr 24, 2026
49.5Accuracy
5
Jun 2, 2026
70.93pass@1
5
Feb 26, 2026
0.923Hypervolume
4
Mar 12, 2026
87.2Hypervolume
4
Mar 12, 2026