List your company

Instruction Following on FollowBench (test)

85.1CSRCRGC
66.48471.31776.1580.983Jun 2, 2026

Evaluation results

MethodLinks
CRGCBase Model=Claude-3.7-Sonnet, Model Type=Closed-source2026.0685.188.686.3
CRGCBase Model=GPT-4o, Model Type=Closed-source2026.0683.887.484.9
CRGCBase Model=Gemini-2.5-Pro, Model Type=Closed-source2026.068386.784.2
CRGCBase Model=Llama-3.1-72B, Model Type=Open-source2026.0681.284.982.3
CRGCBase Model=Qwen2.5-72B, Model Type=Open-source2026.0680.484.281.5
Self-Reflection (SR)Base Model=Claude-3.7-Sonnet, Model Type=Closed-source2026.0680.28481.4
Self-Reflection (SR)Base Model=GPT-4o, Model Type=Closed-source2026.0678.982.780.1
Chain-of-Thoughts (CoT)Base Model=Claude-3.7-Sonnet, Model Type=Closed-source2026.0678.482.179.5
CRGCBase Model=Mixtral-8x22B, Model Type=Open-source2026.0678.38279.4
Self-Reflection (SR)Base Model=Gemini-2.5-Pro, Model Type=Closed-source2026.0678.28279.5
Chain-of-Thoughts (CoT)Base Model=GPT-4o, Model Type=Closed-source2026.0677.180.978.3
Chain-of-Thoughts (CoT)Base Model=Gemini-2.5-Pro, Model Type=Closed-source2026.0676.580.377.8
Self-Reflection (SR)Base Model=Llama-3.1-72B, Model Type=Open-source2026.0675.679.676.8
Self-Reflection (SR)Base Model=Qwen2.5-72B, Model Type=Open-source2026.0674.878.976
Standard Prompting (SP)Base Model=Claude-3.7-Sonnet, Model Type=Closed-source2026.0674.378.275.7
Chain-of-Thoughts (CoT)Base Model=Llama-3.1-72B, Model Type=Open-source2026.0673.877.975
Standard Prompting (SP)Base Model=GPT-4o, Model Type=Closed-source2026.0673.277.374.5
Chain-of-Thoughts (CoT)Base Model=Qwen2.5-72B, Model Type=Open-source2026.0672.977.174.2
Standard Prompting (SP)Base Model=Gemini-2.5-Pro, Model Type=Closed-source2026.0672.776.874
Self-Reflection (SR)Base Model=Mixtral-8x22B, Model Type=Open-source2026.0672.576.673.8
Chain-of-Thoughts (CoT)Base Model=Mixtral-8x22B, Model Type=Open-source2026.0670.874.972.1
Standard Prompting (SP)Base Model=Llama-3.1-72B, Model Type=Open-source2026.067074.271.4
Standard Prompting (SP)Base Model=Qwen2.5-72B, Model Type=Open-source2026.0669.273.570.6
Standard Prompting (SP)Base Model=Mixtral-8x22B, Model Type=Open-source2026.0667.271.468.5