List your company

Multi-turn dialogue on MedDG

86.77Success Rate (SR)MCTS Router
41.883653.536865.1976.8432Apr 14, 2026

Evaluation results

MethodLinks
MCTS RouterCandidate LLM Set=Qwen Series Set2026.0486.774.77
MCTS RouterCandidate LLM Set=Llama Series Set2026.0482.386.41
Greedy RouterCandidate LLM Set=Qwen Series Set2026.0479.714.95
DialRouterCandidate LLM Set=Qwen Series Set2026.0479.034.98
Prompt LLMCandidate LLM Set=Qwen Series Set2026.0472.745.29
Greedy RouterCandidate LLM Set=Llama Series Set2026.0472.516.3
Qwen3-14BCandidate LLM Set=Qwen Series Set2026.0472.55.27
RouterDCCandidate LLM Set=Qwen Series Set2026.0472.55.27
MF RouterCandidate LLM Set=Qwen Series Set2026.0472.414.97
KNN RouterCandidate LLM Set=Qwen Series Set2026.0471.994.75
Qwen3-8BCandidate LLM Set=Qwen Series Set2026.0471.825.02
AvengersCandidate LLM Set=Qwen Series Set2026.0471.695
RandomCandidate LLM Set=Qwen Series Set2026.0471.464.86
Qwen3-4BCandidate LLM Set=Qwen Series Set2026.0471.045.03
DialRouterCandidate LLM Set=Llama Series Set2026.0470.656.16
MF RouterCandidate LLM Set=Llama Series Set2026.0466.196.3
AvengersCandidate LLM Set=Llama Series Set2026.0466.146.65
RouterDCCandidate LLM Set=Llama Series Set2026.0466.096.36
Llama3.1-8B-InstructCandidate LLM Set=Llama Series Set2026.0465.356.19
Prompt LLMCandidate LLM Set=Llama Series Set2026.0465.356.19
KNN RouterCandidate LLM Set=Llama Series Set2026.0464.586.05
RandomCandidate LLM Set=Llama Series Set2026.0461.116.34
Llama3.2-3B-InstructCandidate LLM Set=Llama Series Set2026.0460.786.44
Llama3.2-1B-InstructCandidate LLM Set=Llama Series Set2026.0443.616.97