HealthBench Professional

OpenAI logoGPT-5.6 Sol (August) on HealthBench Professional

Rank 27 of 43, updated November 2, 2026.

GPT-5.6 Sol (August) scores 0.540 on HealthBench Professional, rank 27 of 43 models on the board. The flagship tier of OpenAI's GPT-5.6 family, aimed at its hardest reasoning and agentic workloads. 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.

27
rank of 43
0.540
length-adjusted score
0.566
score before the length adjustment
0.163
gap to the leader, GPT-6 Astra (Anthropic run)
1.05M
context window, tokens
$4.00 / $20.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around GPT-5.6 Sol (August), by length-adjusted score. Differences are against GPT-5.6 Sol (August).

RankModelLength-adjustedBefore the adjustmentDifference
24OpenAI logoGPT-5.6 Luna0.5570.598+0.017
25Google logoGemini 4 Argon0.5510.642+0.011
26Meta logoMuse Spark0.541–+0.001
27OpenAI logoGPT-5.6 Sol (August)0.5400.566–
28Moonshot AI logoKimi K30.5320.569-0.008
29Zhipu logoGLM 5.30.5280.579-0.012
30Anthropic logoClaude Opus 4.70.519–-0.021

Result and API facts

Rank27 of 43
Length-adjusted score0.540
Score before the length adjustment0.566
LabOpenAI
Context window1.05M tokens
API price per 1M tokens$4.00 in / $20.00 out
Licenseproprietary
SourceGPT-5.6 - August Updates (system card addendum) (system card)
Released2026-07-09

Source of this score

Read from GPT-5.6 - August Updates (system card addendum) (system card, OpenAI, 2026-08-06). Vendor-reported. Confidence: verified. Configuration: ChatGPT production (Instant) deployment setting, length-adjusted, GPT-5.6 August Updates PDF column GPT-5.6 Sol (August) (56.6 unadjusted, 2,894 chars).

p. 11, section 5.1 HealthBench, table "Reported as length-adjusted score (unadjusted, mean response length in characters)", column GPT-5.6 Sol (August)full entry on the sources page
HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920)

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.163. Directly above sits Muse Spark at 0.541. Directly below sits Kimi K3 at 0.532. 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-5.6 Sol (August) score on HealthBench Professional?

GPT-5.6 Sol (August) scores 0.540 on HealthBench Professional, which places it at rank 27 of 43 models on the board as of November 2, 2026. The number was read from GPT-5.6 - August Updates (system card addendum), listed on the sources page.

How much does GPT-5.6 Sol (August) cost to run?

GPT-5.6 Sol (August) is priced at $4.00 per million input tokens and $20.00 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-5.6 Sol (August) vs GPT-6 Astra (Anthropic run)
    0.540 vs 0.703, GPT-6 Astra (Anthropic run) by 0.163
  • GPT-5.6 Sol (August) vs Claude Sonnet 5.5
    0.540 vs 0.692, Claude Sonnet 5.5 by 0.152
  • GPT-5.6 Sol (August) vs Claude Fable 5
    0.540 vs 0.660, Claude Fable 5 by 0.120
  • GPT-5.6 Sol (August) vs Claude Opus 5.5
    0.540 vs 0.656, Claude Opus 5.5 by 0.116
  • GPT-5.6 Sol (August) vs GPT-6 Luna (Anthropic run)
    0.540 vs 0.655, GPT-6 Luna (Anthropic run) by 0.115
  • GPT-5.6 Sol (August) vs Claude Haiku 5.5
    0.540 vs 0.648, Claude Haiku 5.5 by 0.108
  • GPT-5.6 Sol (August) vs GPT-6 Astra
    0.540 vs 0.647, GPT-6 Astra by 0.107
  • GPT-5.6 Sol (August) vs GPT-6.1 Sol
    0.540 vs 0.642, GPT-6.1 Sol by 0.102
  • GPT-5.6 Sol (August) vs Claude Fable 5 (September card)
    0.540 vs 0.633, Claude Fable 5 (September card) by 0.093
  • GPT-5.6 Sol (August) vs GPT-6.1 Terra
    0.540 vs 0.627, GPT-6.1 Terra by 0.087
  • GPT-5.6 Sol (August) vs Muse Wonder Full
    0.540 vs 0.623, Muse Wonder Full by 0.083
  • GPT-5.6 Sol (August) vs Claude Fable 5.1
    0.540 vs 0.621, Claude Fable 5.1 by 0.081
  • GPT-5.6 Sol (August) vs GPT-6 Luna
    0.540 vs 0.608, GPT-6 Luna by 0.068
  • GPT-5.6 Sol (August) vs GPT-6 Sol
    0.540 vs 0.608, GPT-6 Sol by 0.068
  • GPT-5.6 Sol (August) vs GPT-5.6 Sol
    0.540 vs 0.605, GPT-5.6 Sol by 0.065
  • GPT-5.6 Sol (August) vs Muse Wonder
    0.540 vs 0.605, Muse Wonder by 0.065
  • GPT-5.6 Sol (August) vs Claude Opus 5
    0.540 vs 0.598, Claude Opus 5 by 0.058
  • GPT-5.6 Sol (August) vs Muse Spark 1.1
    0.540 vs 0.593, Muse Spark 1.1 by 0.053
  • GPT-5.6 Sol (August) vs Claude Sonnet 5
    0.540 vs 0.578, Claude Sonnet 5 by 0.038
  • GPT-5.6 Sol (August) vs GPT-5.6 Terra
    0.540 vs 0.577, GPT-5.6 Terra by 0.037
  • GPT-5.6 Sol (August) vs Claude Opus 4.8 (Opus 4.8 grader)
    0.540 vs 0.574, Claude Opus 4.8 (Opus 4.8 grader) by 0.034
  • GPT-5.6 Sol (August) vs Grok 4.7
    0.540 vs 0.567, Grok 4.7 by 0.027
  • GPT-5.6 Sol (August) vs Claude Opus 4.8
    0.540 vs 0.558, Claude Opus 4.8 by 0.018
  • GPT-5.6 Sol (August) vs GPT-5.6 Luna
    0.540 vs 0.557, GPT-5.6 Luna by 0.017
  • GPT-5.6 Sol (August) vs Gemini 4 Argon
    0.540 vs 0.551, Gemini 4 Argon by 0.011
  • GPT-5.6 Sol (August) vs Muse Spark
    0.540 vs 0.541, Muse Spark by 0.001
  • GPT-5.6 Sol (August) vs Kimi K3
    0.540 vs 0.532, GPT-5.6 Sol (August) by 0.008
  • GPT-5.6 Sol (August) vs GLM 5.3
    0.540 vs 0.528, GPT-5.6 Sol (August) by 0.012
  • GPT-5.6 Sol (August) vs Claude Opus 4.7
    0.540 vs 0.519, GPT-5.6 Sol (August) by 0.021
  • GPT-5.6 Sol (August) vs GPT-5.5
    0.540 vs 0.518, GPT-5.6 Sol (August) by 0.022
  • GPT-5.6 Sol (August) vs Gemini 3.8 Flash
    0.540 vs 0.517, GPT-5.6 Sol (August) by 0.023
  • GPT-5.6 Sol (August) vs DeepSeek V4.1 Flash
    0.540 vs 0.507, GPT-5.6 Sol (August) by 0.033
  • GPT-5.6 Sol (August) vs Grok 4.6
    0.540 vs 0.485, GPT-5.6 Sol (August) by 0.055
  • GPT-5.6 Sol (August) vs GPT-5.4
    0.540 vs 0.481, GPT-5.6 Sol (August) by 0.059
  • GPT-5.6 Sol (August) vs GPT-5
    0.540 vs 0.462, GPT-5.6 Sol (August) by 0.078
  • GPT-5.6 Sol (August) vs GPT-5.2
    0.540 vs 0.459, GPT-5.6 Sol (August) by 0.081
  • GPT-5.6 Sol (August) vs Claude Sonnet 4.6
    0.540 vs 0.442, GPT-5.6 Sol (August) by 0.098
  • GPT-5.6 Sol (August) vs GPT-5.6 Luna (August)
    0.540 vs 0.441, GPT-5.6 Sol (August) by 0.099
  • GPT-5.6 Sol (August) vs GPT-5.1
    0.540 vs 0.396, GPT-5.6 Sol (August) by 0.144
  • GPT-5.6 Sol (August) vs GPT-5.5 Instant
    0.540 vs 0.384, GPT-5.6 Sol (August) by 0.156
  • GPT-5.6 Sol (August) vs MAI-Thinking-1
    0.540 vs 0.350, GPT-5.6 Sol (August) by 0.190
  • GPT-5.6 Sol (August) vs Claude Haiku 4.5
    0.540 vs 0.322, GPT-5.6 Sol (August) by 0.218

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