List your company

Robustness Evaluation on MMLU

88VAccDeepSeek-R1-Distill-LLaMA-8B
40.1652.586577.42Jun 5, 2025

Evaluation results

MethodLinks
DeepSeek-R1-Distill-LLaMA-8BFramework=MASTER2025.0688583034.09
LLaMA-3-8B-InstructFramework=MASTER2025.0669472231.88
Gemma-2-2B-ITFramework=MASTER2025.0648212756.25
LLaMA-3.2-1B-InstructFramework=MASTER2025.064253788.1