General Capability Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90AI2_arc Accuracy
48
Feb 26, 2026
77.78Common Average Score
39
Jun 2, 2026
54.27ARC-C Accuracy
27
Jun 2, 2026
71Average Score
12
May 28, 2026
74.32Score
10
May 12, 2026
66.8General Score
10
May 28, 2026
76.91HS Score
8
Mar 13, 2026
45MMLU
6
Mar 17, 2026
78.84Accuracy
2
Mar 17, 2026