Clinical Question Answering on HealthBench Hard Set
0.3861Overall ScoreOph-Guid-Rag
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Oph-Guid-Rag2026.03 | 0.3861 | 65.76 | 4.83 | 13.33 | 39.69 | 91.67 | |
| GPT-5.22026.03 | 0.2969 | 59.56 | 9.71 | 13.33 | 34.19 | 61.67 |
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Oph-Guid-Rag2026.03 | 0.3861 | 65.76 | 4.83 | 13.33 | 39.69 | 91.67 | |
| GPT-5.22026.03 | 0.2969 | 59.56 | 9.71 | 13.33 | 34.19 | 61.67 |