Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Domain Knowledge on MMLU

80.75MMLU Multi-Domain Knowledge Acc

FP16

20.814836.374951.93567.4951Jan 13, 2026Feb 6, 2026Mar 3, 2026Mar 28, 2026Apr 22, 2026May 17, 2026Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
80.75-
2026.06
80.75-
2026.02
80.17-
2026.02
78.65-1.52
2026.02
78.63-1.54
2026.02
78.62-1.55
2026.02
76.53-3.64
2026.06
75.59-
2026.06
73.97-
2026.06
70.21-
2026.05
67.74-
2026.05
67.48-
2026.02
66.55-
2026.05
63.75-
2026.02
63.55-3
2026.02
63.37-3.18
2026.02
63.3-
2026.02
62.81-3.74
2026.05
62.56-
2026.02
61.64-4.91
2026.02
61.63-1.67
2026.02
61.53-1.77
2026.02
61.15-2.15
2026.01
58.55-
2026.01
58.51-
2026.01
58.37-
2026.01
58.05-
2026.01
57.97-
2026.01
57.86-
2026.01
57.8-
2026.01
57.74-
2026.01
57.74-
2026.01
57.68-
2026.01
57.67-
2026.01
57.63-
2026.01
57.61-
2026.01
57.49-
2026.01
57.48-
2026.01
57.29-
2026.01
56.9-
2026.01
56.89-
2026.01
56.89-
2026.01
56.86-
2026.01
56.42-
2026.01
56.25-
2026.01
55.88-
2026.06
55.38-
2026.01
53.59-
2026.05
49.04-
2026.06
48.21-
2026.02
46.52-
2026.02
44.54-1.98
2026.02
43.89-2.63
2026.02
43.43-3.09
2026.02
41.51-5.01
2026.03
32.01-
2026.03
30.05-
2026.06
27.1-
2026.02
26.79-36.51
2026.05
25.82-
2026.05
25.36-
2026.05
24.75-
2026.05
24.58-
2026.05
24.33-
2026.06
23.71-
2026.06
23.28-
2026.06
23.2-
2026.06
23.12-