General Capability
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.6MMLU Accuracy
74
May 13, 2026
75.9Average Accuracy
66
May 12, 2026
9.14MTBench Score
43
Feb 26, 2026
44Normalized Accuracy
42
Jun 15, 2026
26.77Average Score
30
Apr 14, 2026
52.04Overall Average Score
29
Apr 14, 2026
67.14Average Capability
26
Feb 26, 2026
52Accuracy
14
Jul 3, 2026
51.4Average Score
9
May 8, 2026
43.9Average Score
8
May 12, 2026
91.61S_Gen Score
4
Jun 4, 2026
71.3Accuracy
3
Feb 26, 2026
54Accuracy
3
Feb 26, 2026
70.6Accuracy
3
Feb 26, 2026