Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

General Knowledge Evaluation on MMLU

78.9MMLU Accuracy

Default

22.01236.78151.5566.319Jan 9, 2026Jan 15, 2026Jan 21, 2026Jan 28, 2026Feb 3, 2026Feb 9, 2026Feb 16, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.02
78.9
2026.02
78.7
2026.02
77.8
2026.02
77.3
2026.01
73.01
2026.01
71.93
2026.02
64.4
2026.02
63.9
2026.02
63.8
2026.02
63.7
2026.02
63.6
2026.02
61.9
2026.02
61.2
2026.01
56.69
2026.01
55.68
2026.01
52.99
2026.01
52.51
2026.01
34.56
2026.01
28.65
2026.01
24.2