Patient Simulation on Neutral (test)
69.86BERTScoreSSR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SSRModel=Llama3.1-8B2026.06 | 69.86 | 45.91 | |
| SSRModel=Qwen3-8B2026.06 | 69.57 | 44.44 | |
| UPSDModel=gpt-5.1-chat2026.06 | 64.8 | 38.96 | |
| Patient-ψModel=gpt-5.1-chat2026.06 | 64.62 | 43.56 | |
| UPSDModel=Llama3.1-8B2026.06 | 63.56 | 31.55 | |
| UPSDModel=Qwen3-8B2026.06 | 63.38 | 31.49 | |
| Patient-ψModel=Qwen3-8B2026.06 | 62.62 | 33.61 | |
| BaseModel=Llama3.1-8B2026.06 | 61.52 | 25.88 | |
| Patient-ψModel=Llama3.1-8B2026.06 | 61.39 | 21.06 | |
| BaseModel=Qwen3-8B2026.06 | 56.11 | 31.65 |