GPT-6 Astra on HealthBench Professional
GPT-6 Astra scores 0.647 on HealthBench Professional, rank 7 of 43 models on the board. The first GPT-6 model, shipped September 3, 2026, at twice the input price of GPT-5.6 Sol. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.
Where it sits on the board
The models ranked around GPT-6 Astra, by length-adjusted score. Differences are against GPT-6 Astra.
| Rank | Model | Length-adjusted | Before the adjustment | Difference |
|---|---|---|---|---|
| 4 | 0.656 | 0.771 | +0.009 | |
| 5 | 0.655 | – | +0.008 | |
| 6 | 0.648 | 0.710 | +0.001 | |
| 7 | 0.647 | 0.682 | – | |
| 8 | 0.642 | 0.672 | -0.005 | |
| 9 | 0.633 | 0.689 | -0.014 | |
| 10 | 0.627 | 0.642 | -0.020 |
Result and API facts
| Rank | 7 of 43 |
|---|---|
| Length-adjusted score | 0.647 |
| Score before the length adjustment | 0.682 |
| Lab | OpenAI |
| Context window | 1.05M tokens |
| API price per 1M tokens | $10.00 in / $50.00 out |
| License | proprietary |
| Source | GPT-6 Astra System Card - HealthBench (Deployment Safety Hub) (system card) |
| Released | 2026-09-03 |
Source of this score
Read from GPT-6 Astra System Card - HealthBench (Deployment Safety Hub) (system card, OpenAI, 2026-09-03). Vendor-reported. Confidence: verified. Configuration: length-adjusted, max reasoning effort (68.2 unadjusted, 3,185 mean response chars, as corrected by OpenAI on September 22; first printed as 69.5 and 4,097); GPT-6 Astra system card Table 6, column 'gpt-6 Astra'..
Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119)
Position in the field
The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.056. Directly above sits Claude Haiku 5.5 at 0.648. Directly below sits GPT-6.1 Sol at 0.642. The scores on this page are compiled from published documents rather than from one controlled run, so a small gap between 2 models can reflect a difference in grader version, reasoning effort, or deployment setting as well as a difference in capability.
What does GPT-6 Astra score on HealthBench Professional?
GPT-6 Astra scores 0.647 on HealthBench Professional, which places it at rank 7 of 43 models on the board as of November 2, 2026. The number was read from GPT-6 Astra System Card - HealthBench (Deployment Safety Hub), listed on the sources page.
How much does GPT-6 Astra cost to run?
GPT-6 Astra is priced at $10.00 per million input tokens and $50.00 per million output tokens through OpenAI's API.
Head to head
Score-difference matrixPairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.
- GPT-6 Astra vs GPT-6 Astra (Anthropic run)
- GPT-6 Astra vs Claude Sonnet 5.5
- GPT-6 Astra vs Claude Fable 5
- GPT-6 Astra vs Claude Opus 5.5
- GPT-6 Astra vs GPT-6 Luna (Anthropic run)
- GPT-6 Astra vs Claude Haiku 5.5
- GPT-6 Astra vs GPT-6.1 Sol
- GPT-6 Astra vs Claude Fable 5 (September card)
- GPT-6 Astra vs GPT-6.1 Terra
- GPT-6 Astra vs Muse Wonder Full
- GPT-6 Astra vs Claude Fable 5.1
- GPT-6 Astra vs GPT-6 Luna
- GPT-6 Astra vs GPT-6 Sol
- GPT-6 Astra vs GPT-5.6 Sol
- GPT-6 Astra vs Muse Wonder
- GPT-6 Astra vs Claude Opus 5
- GPT-6 Astra vs Muse Spark 1.1
- GPT-6 Astra vs Claude Sonnet 5
- GPT-6 Astra vs GPT-5.6 Terra
- GPT-6 Astra vs Claude Opus 4.8 (Opus 4.8 grader)
- GPT-6 Astra vs Grok 4.7
- GPT-6 Astra vs Claude Opus 4.8
- GPT-6 Astra vs GPT-5.6 Luna
- GPT-6 Astra vs Gemini 4 Argon
- GPT-6 Astra vs Muse Spark
- GPT-6 Astra vs GPT-5.6 Sol (August)
- GPT-6 Astra vs Kimi K3
- GPT-6 Astra vs GLM 5.3
- GPT-6 Astra vs Claude Opus 4.7
- GPT-6 Astra vs GPT-5.5
- GPT-6 Astra vs Gemini 3.8 Flash
- GPT-6 Astra vs DeepSeek V4.1 Flash
- GPT-6 Astra vs Grok 4.6
- GPT-6 Astra vs GPT-5.4
- GPT-6 Astra vs GPT-5
- GPT-6 Astra vs GPT-5.2
- GPT-6 Astra vs Claude Sonnet 4.6
- GPT-6 Astra vs GPT-5.6 Luna (August)
- GPT-6 Astra vs GPT-5.1
- GPT-6 Astra vs GPT-5.5 Instant
- GPT-6 Astra vs MAI-Thinking-1
- GPT-6 Astra vs Claude Haiku 4.5
Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.