General Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.51Accuracy (ARC)
91
Jun 16, 2026
92.5Accuracy
75
May 12, 2026
74.35Accuracy
56
Jun 23, 2026
87.86MNLI
40
Feb 26, 2026
73.59MMLU Score
39
Apr 20, 2026
48.3Average Accuracy
32
Feb 26, 2026
89.9Average Accuracy
31
Jun 4, 2026
72.45MMLU Accuracy
29
May 27, 2026
72.93Average Accuracy
26
May 12, 2026
59.5ARC-C Accuracy
22
Feb 26, 2026
71.66Chinese Score (CMMLU/CEval)
20
Jun 19, 2026
55.46English Score
20
Jun 19, 2026
65MMLU Accuracy
20
May 29, 2026
71.62Average Score
20
Feb 26, 2026
78.825-shot Accuracy
18
Jul 7, 2026
78.68Accuracy
18
Feb 26, 2026
62.9AIME-2024 Accuracy
16
May 19, 2026
74.6Overall Accuracy
16
Apr 21, 2026
59.5Average Accuracy
16
Jun 29, 2026
48.1Average Score
16
Feb 26, 2026
73Overall Score
16
Jun 8, 2026
73.81Average Accuracy
15
Jun 8, 2026
67.4Accuracy (Average)
15
May 7, 2026
62.3Performance on 8 Sub-Tasks
14
Mar 16, 2026
58.3SciQ Accuracy
14
Mar 6, 2026