List your company

Language Understanding on MMLU 2-order

55.2AccuracyRaw
48.23250.04151.8553.659Mar 17, 2026

Evaluation results

MethodLinks
RawModel=Llama-3.1-8B2026.0355.2
MOSAICModel=Llama-3.1-8B2026.0355.2
SFTModel=Llama-3.1-8B2026.0354.4
ORPOModel=Llama-3.1-8B2026.0354.2
In-contextModel=Llama-3.1-8B2026.0352.9
RawModel=Llama-3.2-3B2026.0350.7
MOSAICModel=Llama-3.2-3B2026.0350.1
ORPOModel=Llama-3.2-3B2026.0349.2
SFTModel=Llama-3.2-3B2026.0348.7
In-contextModel=Llama-3.2-3B2026.0348.5