HealthBench Professional

OpenAI logoGPT-6 Astra on HealthBench Professional

Rank 7 of 43, updated November 2, 2026.

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.

7
rank of 43
0.647
length-adjusted score
0.682
score before the length adjustment
0.056
gap to the leader, GPT-6 Astra (Anthropic run)
1.05M
context window, tokens
$10.00 / $50.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around GPT-6 Astra, by length-adjusted score. Differences are against GPT-6 Astra.

RankModelLength-adjustedBefore the adjustmentDifference
4Anthropic logoClaude Opus 5.50.6560.771+0.009
5OpenAI logoGPT-6 Luna (Anthropic run)0.655–+0.008
6Anthropic logoClaude Haiku 5.50.6480.710+0.001
7OpenAI logoGPT-6 Astra0.6470.682–
8OpenAI logoGPT-6.1 Sol0.6420.672-0.005
9Anthropic logoClaude Fable 5 (September card)0.6330.689-0.014
10OpenAI logoGPT-6.1 Terra0.6270.642-0.020

Result and API facts

Rank7 of 43
Length-adjusted score0.647
Score before the length adjustment0.682
LabOpenAI
Context window1.05M tokens
API price per 1M tokens$10.00 in / $50.00 out
Licenseproprietary
SourceGPT-6 Astra System Card - HealthBench (Deployment Safety Hub) (system card)
Released2026-09-03

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'..

Section 11.4.1, Table 29, HealthBench Professional length-adjusted, GPT-6 Astra column; September 22 correction.3 corroborating documentsfull entry on the sources page
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.

Pairings 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)
    0.647 vs 0.703, GPT-6 Astra (Anthropic run) by 0.056
  • GPT-6 Astra vs Claude Sonnet 5.5
    0.647 vs 0.692, Claude Sonnet 5.5 by 0.045
  • GPT-6 Astra vs Claude Fable 5
    0.647 vs 0.660, Claude Fable 5 by 0.013
  • GPT-6 Astra vs Claude Opus 5.5
    0.647 vs 0.656, Claude Opus 5.5 by 0.009
  • GPT-6 Astra vs GPT-6 Luna (Anthropic run)
    0.647 vs 0.655, GPT-6 Luna (Anthropic run) by 0.008
  • GPT-6 Astra vs Claude Haiku 5.5
    0.647 vs 0.648, Claude Haiku 5.5 by 0.001
  • GPT-6 Astra vs GPT-6.1 Sol
    0.647 vs 0.642, GPT-6 Astra by 0.005
  • GPT-6 Astra vs Claude Fable 5 (September card)
    0.647 vs 0.633, GPT-6 Astra by 0.014
  • GPT-6 Astra vs GPT-6.1 Terra
    0.647 vs 0.627, GPT-6 Astra by 0.020
  • GPT-6 Astra vs Muse Wonder Full
    0.647 vs 0.623, GPT-6 Astra by 0.024
  • GPT-6 Astra vs Claude Fable 5.1
    0.647 vs 0.621, GPT-6 Astra by 0.026
  • GPT-6 Astra vs GPT-6 Luna
    0.647 vs 0.608, GPT-6 Astra by 0.039
  • GPT-6 Astra vs GPT-6 Sol
    0.647 vs 0.608, GPT-6 Astra by 0.039
  • GPT-6 Astra vs GPT-5.6 Sol
    0.647 vs 0.605, GPT-6 Astra by 0.042
  • GPT-6 Astra vs Muse Wonder
    0.647 vs 0.605, GPT-6 Astra by 0.042
  • GPT-6 Astra vs Claude Opus 5
    0.647 vs 0.598, GPT-6 Astra by 0.049
  • GPT-6 Astra vs Muse Spark 1.1
    0.647 vs 0.593, GPT-6 Astra by 0.054
  • GPT-6 Astra vs Claude Sonnet 5
    0.647 vs 0.578, GPT-6 Astra by 0.069
  • GPT-6 Astra vs GPT-5.6 Terra
    0.647 vs 0.577, GPT-6 Astra by 0.070
  • GPT-6 Astra vs Claude Opus 4.8 (Opus 4.8 grader)
    0.647 vs 0.574, GPT-6 Astra by 0.073
  • GPT-6 Astra vs Grok 4.7
    0.647 vs 0.567, GPT-6 Astra by 0.080
  • GPT-6 Astra vs Claude Opus 4.8
    0.647 vs 0.558, GPT-6 Astra by 0.089
  • GPT-6 Astra vs GPT-5.6 Luna
    0.647 vs 0.557, GPT-6 Astra by 0.090
  • GPT-6 Astra vs Gemini 4 Argon
    0.647 vs 0.551, GPT-6 Astra by 0.096
  • GPT-6 Astra vs Muse Spark
    0.647 vs 0.541, GPT-6 Astra by 0.106
  • GPT-6 Astra vs GPT-5.6 Sol (August)
    0.647 vs 0.540, GPT-6 Astra by 0.107
  • GPT-6 Astra vs Kimi K3
    0.647 vs 0.532, GPT-6 Astra by 0.115
  • GPT-6 Astra vs GLM 5.3
    0.647 vs 0.528, GPT-6 Astra by 0.119
  • GPT-6 Astra vs Claude Opus 4.7
    0.647 vs 0.519, GPT-6 Astra by 0.128
  • GPT-6 Astra vs GPT-5.5
    0.647 vs 0.518, GPT-6 Astra by 0.129
  • GPT-6 Astra vs Gemini 3.8 Flash
    0.647 vs 0.517, GPT-6 Astra by 0.130
  • GPT-6 Astra vs DeepSeek V4.1 Flash
    0.647 vs 0.507, GPT-6 Astra by 0.140
  • GPT-6 Astra vs Grok 4.6
    0.647 vs 0.485, GPT-6 Astra by 0.162
  • GPT-6 Astra vs GPT-5.4
    0.647 vs 0.481, GPT-6 Astra by 0.166
  • GPT-6 Astra vs GPT-5
    0.647 vs 0.462, GPT-6 Astra by 0.185
  • GPT-6 Astra vs GPT-5.2
    0.647 vs 0.459, GPT-6 Astra by 0.188
  • GPT-6 Astra vs Claude Sonnet 4.6
    0.647 vs 0.442, GPT-6 Astra by 0.205
  • GPT-6 Astra vs GPT-5.6 Luna (August)
    0.647 vs 0.441, GPT-6 Astra by 0.206
  • GPT-6 Astra vs GPT-5.1
    0.647 vs 0.396, GPT-6 Astra by 0.251
  • GPT-6 Astra vs GPT-5.5 Instant
    0.647 vs 0.384, GPT-6 Astra by 0.263
  • GPT-6 Astra vs MAI-Thinking-1
    0.647 vs 0.350, GPT-6 Astra by 0.297
  • GPT-6 Astra vs Claude Haiku 4.5
    0.647 vs 0.322, GPT-6 Astra by 0.325

Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.