List your company

Multi-turn ambiguous query clarification on ClarifyMT-Bench Partial-Vague persona 1.0

95.5AccuracyGemini-2.5-Flash
34.1450.076681.93Dec 24, 2025

Evaluation results

MethodLinks
Gemini-2.5-Flashvariant=Flash2025.1295.5
Claude-Sonnet-4.5variant=Sonnet2025.1294.8
Llama-3.1-70B-Itparameters=70B, alignment=Instruction-Tuned2025.1285.1
DeepSeek-V32025.1285
GPT-4.12025.1281.9
DeepSeek-R12025.1277.4
Llama-3.1-8B-Itparameters=8B, alignment=Instruction-Tuned2025.1275.6
o32025.1273.3
Qwen-2.5-72B-Itparameters=72B, alignment=Instruction-Tuned2025.1267.7
Qwen-2.5-7B-Itparameters=7B, alignment=Instruction-Tuned2025.1236.5