List your company

Instruction Following on MT-Bench Coding

53.88Original RatioPUAUDIT
49.9850.992552.00553.0175Jun 17, 2026

Evaluation results

MethodLinks
PUAUDITModel=Qwen, n=88842026.0653.8855.241.36
PUAUDITModel=Mistral, n=82402026.0650.1352.132