Diagnostic Dialogue on HG (test)
26.7Recall@1Claude-3.5-Sonnet
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Claude-3.5-SonnetModel category=Large Models2026.02 | 26.7 | 32.9 | 34.5 | 34.5 | 9.4 | |
| SFT (Ours)Model category=Small Models (7B)2026.02 | 25 | 36.1 | 39.4 | 41.8 | 6.9 | |
| GPT-4.1-miniModel category=Large Models2026.02 | 24.3 | 35.7 | 37.6 | 38.3 | 14.1 | |
| Qwen-2.5-72BModel category=Large Models2026.02 | 20.1 | 25.5 | 26 | 26 | 35.2 | |
| Gemini-2.0-FlashModel category=Large Models2026.02 | 18.7 | 24.1 | 25 | 25.1 | 37 | |
| Llama-3.3-70BModel category=Large Models2026.02 | 18.6 | 28.3 | 30.6 | 31.3 | 13.9 | |
| Qwen-2.5 (Base)Model category=Small Models (7B)2026.02 | 17.3 | 21.8 | 21.8 | 22.2 | 12.4 | |
| CoDModel category=Small Models (7B)2026.02 | 10.6 | 14.9 | 19.6 | 20.7 | 2 |