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

Multi-task Language Understanding on MMLU (Score, Speedup)

69.5MMLU Score

LLaMA-3-8B-Instruct

20.93233.54146.1558.759Feb 11, 2026Feb 12, 2026Feb 13, 2026Feb 14, 2026Feb 15, 2026Feb 16, 2026Feb 17, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
69.5-
2026.02
68.5-
2026.02
68.21
2026.02
68.2-
2026.02
68-
2026.02
67.9-
2026.02
67.31
2026.02
66.71.57
2026.02
64.51.98
2026.02
64.41.06
2026.02
63.41.26
2026.02
63.32.08
2026.02
60.21.4
2026.02
22.8-