List your company

Instruction Following on Muses-Bench Aligned n=187

93.16AccuracyDeepseek
40.203253.951667.781.4484Jun 20, 2026

Evaluation results

MethodLinks
DeepseekFramework=Muses-Bench, Mode=Aligned2026.0693.1693.2494.07
QwenFramework=Muses-Bench, Mode=Aligned2026.0691.3691.8691.36
GeminiFramework=Muses-Bench, Mode=Aligned2026.0683.3583.3282.78
GPTFramework=Muses-Bench, Mode=Aligned2026.0642.2456.0754.55