General Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
36.3Average@2
7
Feb 26, 2026
31.6Average@4
7
Feb 26, 2026
75.14Accuracy (5-shot)
7
Feb 26, 2026
92.12Score
7
Feb 26, 2026
92.92Score
7
Feb 26, 2026
82.9MATH
7
Feb 26, 2026
45.4Accuracy (Macro)
6
Jun 25, 2026
71.3P@4
6
May 12, 2026
49.39Pass@1 Accuracy
6
Apr 28, 2026
37.18Pass@1 Accuracy
6
Apr 28, 2026
89.3pass@8
6
Apr 10, 2026
63.32Acc@8
6
Mar 20, 2026
61.6P@1
6
Feb 26, 2026
80.3Score
6
Feb 26, 2026
73.43Overall Accuracy
6
Feb 26, 2026
97.14Score
6
Feb 26, 2026
92.92Score
6
Feb 26, 2026
78.06Accuracy
6
Feb 26, 2026
96.6Score
5
Jul 2, 2026
30.3GSM Score
5
May 21, 2026
91.3Accuracy
5
May 20, 2026
71.2Total Average Score
5
Mar 20, 2026
79CBRC Score
5
Feb 26, 2026
92.3MMLU-R (multi@5 Acc)
4
Jun 1, 2026
27.3Accuracy
4
Apr 13, 2026