General Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98Accuracy
35
May 28, 2026
75.18Avg@8 Accuracy
34
Mar 4, 2026
94.58ARC Score
33
May 26, 2026
70.4Exact Match
33
Feb 26, 2026
69.2Score
32
Feb 26, 2026
90.1Score
32
Feb 26, 2026
72.6Accuracy
31
Jun 9, 2026
63.31Average Accuracy
30
May 19, 2026
86.5Accuracy
30
May 12, 2026
90.5Accuracy
29
May 18, 2026
96.3Accuracy (%)
29
May 18, 2026
37.77Accuracy (General Reasoning)
27
Jun 9, 2026
96.2MMLU General Reasoning Accuracy
25
Jun 2, 2026
93.51Accuracy
24
May 26, 2026
85.1Accuracy
24
Mar 16, 2026
61.8Accuracy
24
Feb 26, 2026
75.6Accuracy
24
Jun 1, 2026
58.8Accuracy
22
Jul 2, 2026
60.4BGQA Accuracy
21
May 11, 2026
87.9Accuracy
21
May 20, 2026
20.38Code Average
21
Mar 19, 2026
38.4Accuracy
21
Feb 26, 2026
75.7Accuracy (General Reasoning)
20
Jul 9, 2026
95.33Accuracy
20
May 28, 2026
73.33Accuracy
20
May 28, 2026