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

Massive Multitask Language Understanding on MMLU

64.6Accuracy

MoE + L_ERC

30.238439.159248.0857.0008Dec 29, 2025Jan 5, 2026Jan 12, 2026Jan 20, 2026Jan 27, 2026Feb 3, 2026Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
64.6
2025.12
63.2
2026.01
59.6
2026.01
58.7
2026.01
58.7
2026.01
58.4
2026.01
57.7
2026.01
57.1
2026.01
56.6
2026.01
55.9
2026.01
55.53
2026.01
55.34
2026.01
55.33
2026.01
55.26
2026.01
55.11
2026.01
55.1
2026.01
55
2026.01
54.98
2026.01
54.97
2026.01
54.9
2026.01
54.79
2026.01
53.6
2026.01
53
2026.01
52
2026.01
50.2
2026.02
46.94
2026.02
44.87
2026.02
44.06
2026.02
42.35
2026.02
34.71
2026.02
31.56