General Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.67Accuracy (NQ General Reasoning)
20
May 28, 2026
97Accuracy
20
May 28, 2026
70Average Accuracy
20
Apr 28, 2026
63.7Accuracy
18
Jun 19, 2026
65.78Average Pass@1 Accuracy
18
Jun 16, 2026
66.8BBL Score
18
May 29, 2026
77.4Accuracy
18
May 14, 2026
85.41Average Score
18
Feb 26, 2026
81.28Pass@1
16
Jun 9, 2026
71.4Average Accuracy
16
Jun 5, 2026
72.7multi@5 Accuracy
16
Jun 1, 2026
77.3Capability
16
Jun 1, 2026
36.1MMLU
16
Feb 26, 2026
75.46Accuracy
16
Mar 20, 2026
46.7Average Accuracy
15
Jul 2, 2026
28.46Avg@k
15
May 13, 2026
35.66Avg@k
15
May 13, 2026
89.2Accuracy
15
May 19, 2026
98.8ID Average Score
15
Apr 23, 2026
52.2Average Score
15
Apr 13, 2026
2.132Speedup Ratio
15
Mar 26, 2026
50.6Accuracy
15
Mar 10, 2026
81.3Accuracy
15
Mar 10, 2026
76.12Pass@3
14
Jun 4, 2026
69.89pass@3
14
Jun 4, 2026