Language Understanding and Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.43MMLU Score
31
Mar 4, 2026
67.8Overall Score
20
May 12, 2026
64.01Average Accuracy
19
Feb 26, 2026
0.082MMLU Score
16
May 15, 2026
46.45MMLU (5s)
13
Feb 26, 2026
58.4ARC-c Accuracy
12
Feb 26, 2026
34.17MMLU
10
May 1, 2026
28.69MMLU
10
Feb 26, 2026
53.16ARC-Challenge Accuracy
9
May 15, 2026
58.28ARC-c
6
Feb 26, 2026
56.81Mean Score
5
Jun 23, 2026
75.9ARC-Easy Accuracy
5
Mar 16, 2026
72.94Average Score
5
Feb 27, 2026
53.1Average Accuracy (%)
2
Jun 29, 2026
50.67PIQA
2
Jun 2, 2026
65.7Arc C Accuracy
2
Mar 31, 2026