Clinical Prediction on EHRSHOT Overall 1.0 (test)
77.2AUROCLocal-Rubric
Evaluation Results
| Method | Links | |
|---|---|---|
| Local-RubricSample Size (n)=All2026.03 | 77.2 | |
| Global-RubricSample Size (n)=All2026.03 | 76.3 | |
| Global-Rubric-AutoSample Size (n)=All2026.03 | 75.6 | |
| Global-Rubric-BlindSample Size (n)=All2026.03 | 75.1 | |
| Global-Rubric-TabularSample Size (n)=All2026.03 | 75.1 | |
| Local-Rubric-GenericSample Size (n)=All2026.03 | 73.8 | |
| CLMBR-TSample Size (n)=All2026.03 | 72.7 | |
| Local-RubricSample Size (n)=402026.03 | 71.7 | |
| Global-RubricSample Size (n)=402026.03 | 70 | |
| NaiveTextSample Size (n)=All2026.03 | 69.9 | |
| Global-Rubric-AutoSample Size (n)=402026.03 | 69.4 | |
| Count-GBMSample Size (n)=All2026.03 | 68.9 | |
| Local-Rubric-GenericSample Size (n)=402026.03 | 68.8 | |
| Global-Rubric-TabularSample Size (n)=402026.03 | 68.6 | |
| Global-Rubric-BlindSample Size (n)=402026.03 | 68.2 | |
| CLMBR-TSample Size (n)=402026.03 | 65.7 | |
| GPT5-Mini-CoTSample Size (n)=02026.03 | 64.4 | |
| NaiveTextSample Size (n)=402026.03 | 63.8 | |
| Qwen3-8B-CoTSample Size (n)=02026.03 | 61 | |
| Count-GBMSample Size (n)=402026.03 | 59.4 |