GPT-5.5 on HealthBench Professional

rank 22 of 31 · updated September 30, 2026

GPT-5.5 scores 0.518 on HealthBench Professional, rank 22 of 31 models on the board. The OpenAI flagship from April 2026, listed here as a comparison row in the GPT-5.6 system card. 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.

Result and API facts

rank	22 of 31
score	0.518
lab	OpenAI
context window	1.05M tokens
API price per 1M tokens	$5.00 in / $30.00 out
license	proprietary
source	GPT-5.6 System Card (system card)
released	2026-04-23

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.185. Directly above sits Claude Opus 4.7 at 0.519. Directly below sits Grok 4.6 at 0.485. 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.

Source of this score

Read from GPT-5.6 System Card (system card, OpenAI, 2026-07-09). Vendor-reported. Confidence: verified. Configuration: length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.5 (57.2 unadjusted, 3818 chars).

HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)

Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.5 · 1 corroborating document · full entry on the sources page

What does GPT-5.5 score on HealthBench Professional?

GPT-5.5 scores 0.518 on HealthBench Professional, which places it at rank 22 of 31 models on the board as of September 30, 2026. The number was read from GPT-5.6 System Card, listed on the sources page.

How much does GPT-5.5 cost to run?

GPT-5.5 is priced at $5.00 per million input tokens and $30.00 per million output tokens through OpenAI's API.

Head to head

Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.

GPT-5.5 vs GPT-6 Astra (Anthropic run)
0.518 vs 0.703 · GPT-6 Astra (Anthropic run) by 0.185
GPT-5.5 vs Claude Sonnet 5.5
0.518 vs 0.692 · Claude Sonnet 5.5 by 0.174
GPT-5.5 vs Claude Fable 5
0.518 vs 0.660 · Claude Fable 5 by 0.142
GPT-5.5 vs Claude Opus 5.5
0.518 vs 0.656 · Claude Opus 5.5 by 0.138
GPT-5.5 vs GPT-6 Astra
0.518 vs 0.647 · GPT-6 Astra by 0.129
GPT-5.5 vs Claude Fable 5 (September card)
0.518 vs 0.633 · Claude Fable 5 (September card) by 0.115
GPT-5.5 vs Claude Fable 5.1
0.518 vs 0.621 · Claude Fable 5.1 by 0.103
GPT-5.5 vs GPT-6 Luna
0.518 vs 0.608 · GPT-6 Luna by 0.090
GPT-5.5 vs GPT-6 Sol
0.518 vs 0.608 · GPT-6 Sol by 0.090
GPT-5.5 vs GPT-5.6 Sol
0.518 vs 0.605 · GPT-5.6 Sol by 0.087
GPT-5.5 vs Claude Opus 5
0.518 vs 0.598 · Claude Opus 5 by 0.080
GPT-5.5 vs Muse Spark 1.1
0.518 vs 0.593 · Muse Spark 1.1 by 0.075
GPT-5.5 vs Claude Sonnet 5
0.518 vs 0.578 · Claude Sonnet 5 by 0.060
GPT-5.5 vs GPT-5.6 Terra
0.518 vs 0.577 · GPT-5.6 Terra by 0.059
GPT-5.5 vs Claude Opus 4.8 (Opus 4.8 grader)
0.518 vs 0.574 · Claude Opus 4.8 (Opus 4.8 grader) by 0.056
GPT-5.5 vs Grok 4.7
0.518 vs 0.567 · Grok 4.7 by 0.049
GPT-5.5 vs Claude Opus 4.8
0.518 vs 0.558 · Claude Opus 4.8 by 0.040
GPT-5.5 vs GPT-5.6 Luna
0.518 vs 0.557 · GPT-5.6 Luna by 0.039
GPT-5.5 vs Muse Spark
0.518 vs 0.541 · Muse Spark by 0.023
GPT-5.5 vs GPT-5.6 Sol (August)
0.518 vs 0.540 · GPT-5.6 Sol (August) by 0.022
GPT-5.5 vs Claude Opus 4.7
0.518 vs 0.519 · Claude Opus 4.7 by 0.001
GPT-5.5 vs Grok 4.6
0.518 vs 0.485 · GPT-5.5 by 0.033
GPT-5.5 vs GPT-5.4
0.518 vs 0.481 · GPT-5.5 by 0.037
GPT-5.5 vs GPT-5
0.518 vs 0.462 · GPT-5.5 by 0.056
GPT-5.5 vs GPT-5.2
0.518 vs 0.459 · GPT-5.5 by 0.059
GPT-5.5 vs Claude Sonnet 4.6
0.518 vs 0.442 · GPT-5.5 by 0.076
GPT-5.5 vs GPT-5.6 Luna (August)
0.518 vs 0.441 · GPT-5.5 by 0.077
GPT-5.5 vs GPT-5.1
0.518 vs 0.396 · GPT-5.5 by 0.122
GPT-5.5 vs GPT-5.5 Instant
0.518 vs 0.384 · GPT-5.5 by 0.134
GPT-5.5 vs MAI-Thinking-1
0.518 vs 0.350 · GPT-5.5 by 0.168

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