Multi-turn dialogue on ShareGPT, JDDC, and MedDG Aggregated
89.77SRavgMCTS Router
Evaluation Results
| Method | Links | |
|---|---|---|
| MCTS RouterCandidate LLM Set=Qwen Series Set2026.04 | 89.77 | |
| MCTS RouterCandidate LLM Set=Llama Series Set2026.04 | 86.53 | |
| Greedy RouterCandidate LLM Set=Qwen Series Set2026.04 | 83.94 | |
| DialRouterCandidate LLM Set=Qwen Series Set2026.04 | 83.31 | |
| Greedy RouterCandidate LLM Set=Llama Series Set2026.04 | 79.7 | |
| DialRouterCandidate LLM Set=Llama Series Set2026.04 | 78.88 | |
| AvengersCandidate LLM Set=Qwen Series Set2026.04 | 78 | |
| KNN RouterCandidate LLM Set=Qwen Series Set2026.04 | 77.93 | |
| Qwen3-14BCandidate LLM Set=Qwen Series Set2026.04 | 77.64 | |
| RouterDCCandidate LLM Set=Qwen Series Set2026.04 | 77.47 | |
| Prompt LLMCandidate LLM Set=Qwen Series Set2026.04 | 77.36 | |
| MF RouterCandidate LLM Set=Qwen Series Set2026.04 | 77.14 | |
| Qwen3-8BCandidate LLM Set=Qwen Series Set2026.04 | 76.92 | |
| RandomCandidate LLM Set=Qwen Series Set2026.04 | 76.52 | |
| Qwen3-4BCandidate LLM Set=Qwen Series Set2026.04 | 75.41 | |
| KNN RouterCandidate LLM Set=Llama Series Set2026.04 | 73.7 | |
| RouterDCCandidate LLM Set=Llama Series Set2026.04 | 73.6 | |
| AvengersCandidate LLM Set=Llama Series Set2026.04 | 73.5 | |
| MF RouterCandidate LLM Set=Llama Series Set2026.04 | 72.75 | |
| Llama3.1-8B-InstructCandidate LLM Set=Llama Series Set2026.04 | 72.6 | |
| Prompt LLMCandidate LLM Set=Llama Series Set2026.04 | 72.34 | |
| RandomCandidate LLM Set=Llama Series Set2026.04 | 68.75 | |
| Llama3.2-3B-InstructCandidate LLM Set=Llama Series Set2026.04 | 68.4 | |
| Llama3.2-1B-InstructCandidate LLM Set=Llama Series Set2026.04 | 51.57 |