List your company

Multi-turn information acquisition on Fashion

83.77Success Rate (SR)CUP
13.143631.479349.81568.1507Apr 5, 2026

Evaluation results

MethodLinks
CUPModel=Mistral-7B-v0.32026.0483.774.11
CUPModel=Qwen3-4B2026.0483.414.16
CUPModel=Llama-3.1-8B2026.0482.24.01
MISQ-HFModel=Llama-3.1-8B2026.0463.444.18
MISQ-HFModel=Mistral-7B-v0.32026.0459.324.16
BED-LLMModel=Llama-3.1-8B2026.0459.324.4
MISQ-HFModel=Qwen3-4B2026.0456.414.2
ATDModel=Llama-3.1-8B2026.0452.34.6
UoTModel=Llama-3.1-8B2026.0452.064.73
BED-LLMModel=Qwen3-4B2026.0451.824.38
UoTModel=Mistral-7B-v0.32026.0450.854.77
BED-LLMModel=Mistral-7B-v0.32026.0450.244.45
UoTModel=Qwen3-4B2026.0449.524.8
ATDModel=Mistral-7B-v0.32026.0448.674.62
ATDModel=Qwen3-4B2026.0448.434.62
LLM-planningModel=Mistral-7B-v0.32026.0441.654.69
LLM-planningModel=Qwen3-4B2026.0441.534.7
LLM-planningModel=Llama-3.1-8B2026.0440.684.73
CoTModel=Qwen3-4B2026.0439.234.05
CoTModel=Llama-3.1-8B2026.0438.624.13
CoTModel=Mistral-7B-v0.32026.0438.144.01
Direct PromptingModel=Qwen3-4B2026.0437.654.13
Direct PromptingModel=Llama-3.1-8B2026.0435.234.21
Direct PromptingModel=Mistral-7B-v0.32026.0433.94.18
SBERT2026.0415.864.79