General Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82.51Pass@1
11
May 13, 2026
63.8Average Accuracy
11
Feb 27, 2026
67.75Pass@1
10
Jun 9, 2026
77.4Pass@1
10
Mar 24, 2026
86.51Accuracy
10
Jun 18, 2026
8.8Accuracy (Reasoning GYM)
10
Feb 27, 2026
79.2Score
9
Jul 2, 2026
57.5General Reasoning Score
9
Jul 2, 2026
89.9Score
9
Jul 2, 2026
95.5Accuracy
9
Jun 2, 2026
98.7Accuracy
9
Jun 2, 2026
32.47Accuracy (General Reasoning)
9
May 27, 2026
89.9Accuracy
9
May 27, 2026
4.82SpeedUp
9
May 12, 2026
55.8MMLU Accuracy
8
Jun 19, 2026
13.2GPQA Score
8
Jun 11, 2026
52Average Score
8
Jun 9, 2026
59.2Accuracy
8
May 26, 2026
89.4Accuracy
8
May 26, 2026
54.1Avg @1 Score
8
Apr 3, 2026
64.1Accuracy
8
Mar 20, 2026
66.1Performance Score (BBH General Reasoning)
8
Apr 30, 2026
64.75Pass@1 Accuracy
8
Feb 26, 2026
44.1Accuracy
7
Jun 30, 2026
86.61Average Accuracy
7
Apr 6, 2026