HealthBench Professional (Length-Adjusted)
Professional Work · 2026-04-30
HealthBench Professional evaluates real clinical work using 525 physician-authored conversations spanning care consultations, writing and documentation, and medical research. This metric applies the benchmark's published length adjustment to penalize unnecessarily verbose responses.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Mythos 5 | 66.0 |
| Claude Fable 5 | 60.9 |
| GPT-5.6 Sol | 60.5 |
| Claude Opus 5 | 59.8 |
| Sonnet 5 | 57.8 |
| GPT-5.6 Terra | 57.7 |
| Opus 4.8 | 57.4 |
| GPT-5.6 Luna | 55.7 |
| GPT-5.4 | 48.1 |
| GPT-5 | 46.2 |
| GPT-5.2 | 45.9 |
| GPT-5.1 | 39.6 |
| GPT-5.5 Instant | 38.4 |
| GPT-5.1 Instant | 37.6 |
| GPT-5.2 Instant | 35.7 |
| GPT-5.3 Instant | 32.9 |