GPT-5.2 on HealthBench Professional
rank 17 of 22 · updated September 8, 2026
GPT-5.2 scores 0.459 on HealthBench Professional, rank 17 of 22 models on the board. The December 2025 OpenAI release, a comparison row carried over from 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 | 17 of 22 |
|---|---|
| score | 0.459 |
| lab | OpenAI |
| context window | 400K tokens |
| API price per 1M tokens | $1.75 in / $14.00 out |
| license | proprietary |
| source | GPT-5.6 System Card (system card) |
| released | 2025-12-11 |
Position in the field
The gap to the leader, Claude Fable 5 at 0.660, is 0.201. Directly above sits GPT-5 at 0.462. Directly below sits Claude Sonnet 4.6 at 0.442. 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-5.2 (50.0 unadjusted, 3400 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-5.2 · 1 corroborating document · full entry on the sources page
What does GPT-5.2 score on HealthBench Professional?
GPT-5.2 scores 0.459 on HealthBench Professional, which places it at rank 17 of 22 models on the board as of September 8, 2026. The number was read from GPT-5.6 System Card, listed on the sources page.
How much does GPT-5.2 cost to run?
GPT-5.2 is priced at $1.75 per million input tokens and $14.00 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-5.2 vs Claude Fable 50.459 vs 0.660 · Claude Fable 5 by 0.201
- GPT-5.2 vs GPT-6 Astra0.459 vs 0.634 · GPT-6 Astra by 0.175
- GPT-5.2 vs Claude Fable 5.10.459 vs 0.621 · Claude Fable 5.1 by 0.162
- GPT-5.2 vs GPT-5.6 Sol0.459 vs 0.605 · GPT-5.6 Sol by 0.146
- GPT-5.2 vs Claude Opus 50.459 vs 0.598 · Claude Opus 5 by 0.139
- GPT-5.2 vs Muse Spark 1.10.459 vs 0.593 · Muse Spark 1.1 by 0.134
- GPT-5.2 vs Claude Sonnet 50.459 vs 0.578 · Claude Sonnet 5 by 0.119
- GPT-5.2 vs GPT-5.6 Terra0.459 vs 0.577 · GPT-5.6 Terra by 0.118
- GPT-5.2 vs Claude Opus 4.80.459 vs 0.558 · Claude Opus 4.8 by 0.099
- GPT-5.2 vs GPT-5.6 Luna0.459 vs 0.557 · GPT-5.6 Luna by 0.098
- GPT-5.2 vs Muse Spark0.459 vs 0.541 · Muse Spark by 0.082
- GPT-5.2 vs GPT-5.6 Sol (August)0.459 vs 0.540 · GPT-5.6 Sol (August) by 0.081
- GPT-5.2 vs Claude Opus 4.70.459 vs 0.519 · Claude Opus 4.7 by 0.060
- GPT-5.2 vs GPT-5.50.459 vs 0.518 · GPT-5.5 by 0.059
- GPT-5.2 vs GPT-5.40.459 vs 0.481 · GPT-5.4 by 0.022
- GPT-5.2 vs GPT-50.459 vs 0.462 · GPT-5 by 0.003
- GPT-5.2 vs Claude Sonnet 4.60.459 vs 0.442 · GPT-5.2 by 0.017
- GPT-5.2 vs GPT-5.6 Luna (August)0.459 vs 0.441 · GPT-5.2 by 0.018
- GPT-5.2 vs GPT-5.10.459 vs 0.396 · GPT-5.2 by 0.063
- GPT-5.2 vs GPT-5.5 Instant0.459 vs 0.384 · GPT-5.2 by 0.075
- GPT-5.2 vs MAI-Thinking-10.459 vs 0.350 · GPT-5.2 by 0.109
Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.