Therapeutic Dimension Classification on CheeseBurger
48.96AccuracyCARE
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| CAREEvaluation Protocol=Zero-shot2026.04 | 48.96 | 20.46 | 28.28 | 20.07 | 50.3 | 65.25 | 48.96 | |
| QwenEvaluation Protocol=Zero-shot2026.04 | 28.05 | 11.25 | 10.71 | 16.58 | 26.94 | 29.35 | 28.05 | |
| GPT-4oEvaluation Protocol=Zero-shot2026.04 | 26.33 | 12.62 | 19.61 | 10.14 | 31.5 | 42.22 | 26.33 | |
| Llama 3.2Evaluation Protocol=Zero-shot2026.04 | 23.15 | 9.01 | 16.98 | 17.89 | 18.95 | 39.13 | 23.15 |