List your company

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

69.5MMLU ScoreLLaMA-3-8B-Instruct
20.93233.54146.1558.759Feb 11, 2026Feb 12, 2026Feb 13, 2026Feb 14, 2026Feb 15, 2026Feb 16, 2026Feb 17, 2026

Evaluation results

MethodLinks
LLaMA-3-8B-InstructData=ZsRE 10K2026.0269.5—
CrispEditData=ZsRE 10K2026.0268.5—
Full DecodingBackbone=Dream-7B2026.0268.21
Adam-NSCLData=ZsRE 10K2026.0268.2—
LocBF-FTData=ZsRE 10K2026.0268—
UltraEditData=ZsRE 10K2026.0267.9—
Full DecodingBackbone=LLaDA-8B2026.0267.31
JotBackbone=Dream-7B2026.0266.71.57
JotBackbone=LLaDA-8B2026.0264.51.98
KLASSBackbone=Dream-7B2026.0264.41.06
KLASSBackbone=LLaDA-8B2026.0263.41.26
ProphetBackbone=LLaDA-8B2026.0263.32.08
ProphetBackbone=Dream-7B2026.0260.21.4
AlphaEditData=ZsRE 10K2026.0222.8—