Reasoning on StethoBench
48.8ROUGE-1StethoLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| StethoLM2026.02 | 48.8 | 35.1 | |
| Qwen2.5-Omni2026.02 | 26.7 | 14.1 | |
| Gama2026.02 | 19.6 | 9.5 | |
| LTU2026.02 | 18.7 | 7.3 | |
| Gemma3N2026.02 | 18.6 | 8.6 | |
| LLM2026.02 | 13.9 | 6.2 | |
| Gemini-2.5-Flash2026.02 | 10.3 | 14.2 | |
| Pengi2026.02 | 1.7 | 0.5 |