Clinical Intent Alignment on HealthBench
60.12CIAretrieval-augmented multi-agent framework
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| retrieval-augmented multi-agent frameworkRubric=Ours2026.01 | 60.12 | — | — | |
| GPT-4o RubricRubric=GPT-4o2026.01 | 55.16 | — | — | |
| Generic RubricRubric=Generic2026.01 | 19.66 | — | — |