HealthBench Professional

OpenAI logoGPT-5.5 Instant on HealthBench Professional

Rank 41 of 43, updated November 2, 2026.

GPT-5.5 Instant scores 0.384 on HealthBench Professional, rank 41 of 43 models on the board. The fast variant that became ChatGPT's default model in May 2026. 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.

41
rank of 43
0.384
length-adjusted score
0.407
score before the length adjustment
0.319
gap to the leader, GPT-6 Astra (Anthropic run)
400K
context window, tokens
$5.00 / $30.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around GPT-5.5 Instant, by length-adjusted score. Differences are against GPT-5.5 Instant.

RankModelLength-adjustedBefore the adjustmentDifference
37OpenAI logoGPT-5.20.4590.500+0.075
38Anthropic logoClaude Sonnet 4.60.442–+0.058
39OpenAI logoGPT-5.6 Luna (August)0.4410.468+0.057
40OpenAI logoGPT-5.10.3960.480+0.012
41OpenAI logoGPT-5.5 Instant0.3840.407–
42Microsoft logoMAI-Thinking-10.350–-0.034
43Anthropic logoClaude Haiku 4.50.322–-0.062

Result and API facts

Rank41 of 43
Length-adjusted score0.384
Score before the length adjustment0.407
LabOpenAI
Context window400K tokens
API price per 1M tokens$5.00 in / $30.00 out
Licenseproprietary
SourceGPT-5.5 Instant System Card (system card)
Released2026-05-05

Source of this score

Read from GPT-5.5 Instant System Card (system card, OpenAI, 2026-05-05). Vendor-reported. Confidence: verified. Configuration: length-adjusted (40.7 unadjusted, 2,775 mean response chars); GPT-5.5 Instant system card Table 5, column GPT-5.5 INSTANT..

Section 4.1 HealthBench, Table 5 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.5 INSTANT1 corroborating documentfull entry on the sources page
HealthBench Professional 37.6 (40.4, 2,973) 35.7 (38.3, 2,872) 32.9 (33.8, 2,285) 38.4 (40.7, 2,775)

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.319. Directly above sits GPT-5.1 at 0.396. Directly below sits MAI-Thinking-1 at 0.350. 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-5.5 Instant score on HealthBench Professional?

GPT-5.5 Instant scores 0.384 on HealthBench Professional, which places it at rank 41 of 43 models on the board as of November 2, 2026. The number was read from GPT-5.5 Instant System Card, listed on the sources page.

How much does GPT-5.5 Instant cost to run?

GPT-5.5 Instant is priced at $5.00 per million input tokens and $30.00 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-5.5 Instant vs GPT-6 Astra (Anthropic run)
    0.384 vs 0.703, GPT-6 Astra (Anthropic run) by 0.319
  • GPT-5.5 Instant vs Claude Sonnet 5.5
    0.384 vs 0.692, Claude Sonnet 5.5 by 0.308
  • GPT-5.5 Instant vs Claude Fable 5
    0.384 vs 0.660, Claude Fable 5 by 0.276
  • GPT-5.5 Instant vs Claude Opus 5.5
    0.384 vs 0.656, Claude Opus 5.5 by 0.272
  • GPT-5.5 Instant vs GPT-6 Luna (Anthropic run)
    0.384 vs 0.655, GPT-6 Luna (Anthropic run) by 0.271
  • GPT-5.5 Instant vs Claude Haiku 5.5
    0.384 vs 0.648, Claude Haiku 5.5 by 0.264
  • GPT-5.5 Instant vs GPT-6 Astra
    0.384 vs 0.647, GPT-6 Astra by 0.263
  • GPT-5.5 Instant vs GPT-6.1 Sol
    0.384 vs 0.642, GPT-6.1 Sol by 0.258
  • GPT-5.5 Instant vs Claude Fable 5 (September card)
    0.384 vs 0.633, Claude Fable 5 (September card) by 0.249
  • GPT-5.5 Instant vs GPT-6.1 Terra
    0.384 vs 0.627, GPT-6.1 Terra by 0.243
  • GPT-5.5 Instant vs Muse Wonder Full
    0.384 vs 0.623, Muse Wonder Full by 0.239
  • GPT-5.5 Instant vs Claude Fable 5.1
    0.384 vs 0.621, Claude Fable 5.1 by 0.237
  • GPT-5.5 Instant vs GPT-6 Luna
    0.384 vs 0.608, GPT-6 Luna by 0.224
  • GPT-5.5 Instant vs GPT-6 Sol
    0.384 vs 0.608, GPT-6 Sol by 0.224
  • GPT-5.5 Instant vs GPT-5.6 Sol
    0.384 vs 0.605, GPT-5.6 Sol by 0.221
  • GPT-5.5 Instant vs Muse Wonder
    0.384 vs 0.605, Muse Wonder by 0.221
  • GPT-5.5 Instant vs Claude Opus 5
    0.384 vs 0.598, Claude Opus 5 by 0.214
  • GPT-5.5 Instant vs Muse Spark 1.1
    0.384 vs 0.593, Muse Spark 1.1 by 0.209
  • GPT-5.5 Instant vs Claude Sonnet 5
    0.384 vs 0.578, Claude Sonnet 5 by 0.194
  • GPT-5.5 Instant vs GPT-5.6 Terra
    0.384 vs 0.577, GPT-5.6 Terra by 0.193
  • GPT-5.5 Instant vs Claude Opus 4.8 (Opus 4.8 grader)
    0.384 vs 0.574, Claude Opus 4.8 (Opus 4.8 grader) by 0.190
  • GPT-5.5 Instant vs Grok 4.7
    0.384 vs 0.567, Grok 4.7 by 0.183
  • GPT-5.5 Instant vs Claude Opus 4.8
    0.384 vs 0.558, Claude Opus 4.8 by 0.174
  • 0.384 vs 0.557, GPT-5.6 Luna by 0.173
  • GPT-5.5 Instant vs Gemini 4 Argon
    0.384 vs 0.551, Gemini 4 Argon by 0.167
  • GPT-5.5 Instant vs Muse Spark
    0.384 vs 0.541, Muse Spark by 0.157
  • GPT-5.5 Instant vs GPT-5.6 Sol (August)
    0.384 vs 0.540, GPT-5.6 Sol (August) by 0.156
  • GPT-5.5 Instant vs Kimi K3
    0.384 vs 0.532, Kimi K3 by 0.148
  • GPT-5.5 Instant vs GLM 5.3
    0.384 vs 0.528, GLM 5.3 by 0.144
  • GPT-5.5 Instant vs Claude Opus 4.7
    0.384 vs 0.519, Claude Opus 4.7 by 0.135
  • GPT-5.5 Instant vs GPT-5.5
    0.384 vs 0.518, GPT-5.5 by 0.134
  • GPT-5.5 Instant vs Gemini 3.8 Flash
    0.384 vs 0.517, Gemini 3.8 Flash by 0.133
  • GPT-5.5 Instant vs DeepSeek V4.1 Flash
    0.384 vs 0.507, DeepSeek V4.1 Flash by 0.123
  • GPT-5.5 Instant vs Grok 4.6
    0.384 vs 0.485, Grok 4.6 by 0.101
  • GPT-5.5 Instant vs GPT-5.4
    0.384 vs 0.481, GPT-5.4 by 0.097
  • GPT-5.5 Instant vs GPT-5
    0.384 vs 0.462, GPT-5 by 0.078
  • GPT-5.5 Instant vs GPT-5.2
    0.384 vs 0.459, GPT-5.2 by 0.075
  • GPT-5.5 Instant vs Claude Sonnet 4.6
    0.384 vs 0.442, Claude Sonnet 4.6 by 0.058
  • GPT-5.5 Instant vs GPT-5.6 Luna (August)
    0.384 vs 0.441, GPT-5.6 Luna (August) by 0.057
  • GPT-5.5 Instant vs GPT-5.1
    0.384 vs 0.396, GPT-5.1 by 0.012
  • GPT-5.5 Instant vs MAI-Thinking-1
    0.384 vs 0.350, GPT-5.5 Instant by 0.034
  • GPT-5.5 Instant vs Claude Haiku 4.5
    0.384 vs 0.322, GPT-5.5 Instant by 0.062

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