List your company

Question Answering on MMLU-Pro (Subject-Specific ACC/LEN)

25.7Law AccuracyMERA
21.22822.38923.5524.711Aug 6, 2025

Evaluation results

MethodLinks
MERABase Model=DeepSeek-R1-Distill-Qwen-7B2025.0825.781428.54,09236.93,854
FCS+Ref.Base Model=DeepSeek-R1-Distill-Qwen-7B2025.0824.197327.95,51834.95,098
OriginalBase Model=DeepSeek-R1-Distill-Qwen-7B2025.0823.51,52826.45,41234.14,978
O1-PrunerBase Model=DeepSeek-R1-Distill-Qwen-7B2025.0822.81,05425.64,98135.64,587
DASTBase Model=DeepSeek-R1-Distill-Qwen-7B2025.0821.41,24927.15,82133.55,243