# HealthBench Professional (raw) — AI model rankings

physician-graded conversations, scored before adjustment for answer length

9 tracked models have a published HealthBench Professional (raw) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Claude Opus 5.5 | Anthropic | 77.1% | Lab | Sep 22 2026 |
| 1 | Claude Sonnet 5.5 | Anthropic | 77.1% | Lab | Sep 28 2026 |
| 3 | Claude Fable 5.1 | Anthropic | 74.2% | Lab | Sep 1 2026 |
| 4 | Claude Opus 5 | Anthropic | 73.4% | Lab | Jul 24 2026 |
| 5 | Claude Haiku 5.5 | Anthropic | 71% | Lab | Oct 7 2026 |
| 6 | Claude Mythos 5 | Anthropic | 70.3% | Lab | Jun 9 2026 |
| 7 | Claude Fable 5 | Anthropic | 68.9% | Lab | Jun 9 2026 |
| 8 | Claude Sonnet 5 | Anthropic | 62.4% | Lab | Jun 30 2026 |
| 9 | Claude Opus 4.8 | Anthropic | 60.3% | Lab | May 28 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/healthbench-professional-raw
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.