# HealthBench Professional leaderboard

Knowledge benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/knowledge-health-bench-professional

Every model the catalog carries a published HealthBench Professional value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Rubric-graded open-ended responses |
| Tasks | Clinician chat tasks |
| Difficulty | Professional clinical workflows |
| Published by | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |

An open benchmark for clinician-facing model responses across care consult, writing and documentation, and medical research tasks.

## HealthBench Professional ranking

21 models with a published HealthBench Professional value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Rubric-graded open-ended responses | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 69.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 66.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.2 Sol](https://modelchoice.dev/models/gpt-6-2-sol) | OpenAI | 65.9 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 65.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Ling 3.1 Flash](https://modelchoice.dev/models/ling-3-1-flash) | InclusionAI | 65.3 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 64.7 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 64.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 62.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Muse Wonder Full](https://modelchoice.dev/models/muse-wonder-full) | Meta | 62.3 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 60.5 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Muse Wonder](https://modelchoice.dev/models/muse-wonder) | Meta | 60.5 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen4 Max](https://modelchoice.dev/models/qwen4-max) | Alibaba | 60.0 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 59.8 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 17 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 57.7 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 56.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 55.7 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Ling 3.0 Flash Sante](https://modelchoice.dev/models/ling-3-0-flash-sante) | InclusionAI | 54.3 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 48.1 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
