List your company

Multi-turn ambiguous query clarification on ClarifyMT-Bench Off-Focus persona 1.0

96.1AccuracyClaude-Sonnet-4.5
58.86868.53478.287.866Dec 24, 2025

Evaluation results

MethodLinks
Claude-Sonnet-4.5variant=Sonnet2025.1296.1
Gemini-2.5-Flashvariant=Flash2025.1294.5
Llama-3.1-70B-Itparameters=70B, alignment=Instruction-Tuned2025.1290.9
GPT-4.12025.1289.1
Llama-3.1-8B-Itparameters=8B, alignment=Instruction-Tuned2025.1287.5
DeepSeek-V32025.1282.1
Qwen-2.5-72B-Itparameters=72B, alignment=Instruction-Tuned2025.1278.9
DeepSeek-R12025.1278.8
o32025.1276.8
Qwen-2.5-7B-Itparameters=7B, alignment=Instruction-Tuned2025.1260.3