Claude Sonnet 5.5 on HealthBench Professional

rank 2 of 31 · updated September 30, 2026

Claude Sonnet 5.5 scores 0.692 on HealthBench Professional, rank 2 of 31 models on the board. 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	2 of 31
score	0.692
lab	Anthropic
context window	1M tokens
API price per 1M tokens	$2.00 in / $10.00 out
license	proprietary
source	Claude Sonnet 5.5 System Card (system card)
released	2026-09-28

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.011. Directly below sits Claude Fable 5 at 0.660. 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 Claude Sonnet 5.5 System Card (system card, Anthropic, 2026-09-28). Vendor-reported. Confidence: verified. Configuration: Anthropic; max effort; Opus 4.8 grader; safety classifiers enabled; length-adjusted; raw 77.1%.

On HealthBench Professional at max effort, length adjustment changes the ranking. After: GPT-6 Astra (70.3%) > Claude Sonnet 5.5 (69.2%) > Claude Opus 5.5 (65.6%) > Claude Fable 5.1 (62.1%).

p. 138, Section 8.15.2 and paragraph above Figure 8.15.B. · full entry on the sources page

What does Claude Sonnet 5.5 score on HealthBench Professional?

Claude Sonnet 5.5 scores 0.692 on HealthBench Professional, which places it at rank 2 of 31 models on the board as of September 30, 2026. The number was read from Claude Sonnet 5.5 System Card, listed on the sources page.

How much does Claude Sonnet 5.5 cost to run?

Claude Sonnet 5.5 is priced at $2.00 per million input tokens and $10.00 per million output tokens through Anthropic's API.

Head to head

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

Claude Sonnet 5.5 vs GPT-6 Astra (Anthropic run)
0.692 vs 0.703 · GPT-6 Astra (Anthropic run) by 0.011
Claude Sonnet 5.5 vs Claude Fable 5
0.692 vs 0.660 · Claude Sonnet 5.5 by 0.032
Claude Sonnet 5.5 vs Claude Opus 5.5
0.692 vs 0.656 · Claude Sonnet 5.5 by 0.036
Claude Sonnet 5.5 vs GPT-6 Astra
0.692 vs 0.647 · Claude Sonnet 5.5 by 0.045
Claude Sonnet 5.5 vs Claude Fable 5 (September card)
0.692 vs 0.633 · Claude Sonnet 5.5 by 0.059
Claude Sonnet 5.5 vs Claude Fable 5.1
0.692 vs 0.621 · Claude Sonnet 5.5 by 0.071
Claude Sonnet 5.5 vs GPT-6 Luna
0.692 vs 0.608 · Claude Sonnet 5.5 by 0.084
Claude Sonnet 5.5 vs GPT-6 Sol
0.692 vs 0.608 · Claude Sonnet 5.5 by 0.084
Claude Sonnet 5.5 vs GPT-5.6 Sol
0.692 vs 0.605 · Claude Sonnet 5.5 by 0.087
Claude Sonnet 5.5 vs Claude Opus 5
0.692 vs 0.598 · Claude Sonnet 5.5 by 0.094
Claude Sonnet 5.5 vs Muse Spark 1.1
0.692 vs 0.593 · Claude Sonnet 5.5 by 0.099
Claude Sonnet 5.5 vs Claude Sonnet 5
0.692 vs 0.578 · Claude Sonnet 5.5 by 0.114
Claude Sonnet 5.5 vs GPT-5.6 Terra
0.692 vs 0.577 · Claude Sonnet 5.5 by 0.115
Claude Sonnet 5.5 vs Claude Opus 4.8 (Opus 4.8 grader)
0.692 vs 0.574 · Claude Sonnet 5.5 by 0.118
Claude Sonnet 5.5 vs Grok 4.7
0.692 vs 0.567 · Claude Sonnet 5.5 by 0.125
Claude Sonnet 5.5 vs Claude Opus 4.8
0.692 vs 0.558 · Claude Sonnet 5.5 by 0.134
Claude Sonnet 5.5 vs GPT-5.6 Luna
0.692 vs 0.557 · Claude Sonnet 5.5 by 0.135
Claude Sonnet 5.5 vs Muse Spark
0.692 vs 0.541 · Claude Sonnet 5.5 by 0.151
Claude Sonnet 5.5 vs GPT-5.6 Sol (August)
0.692 vs 0.540 · Claude Sonnet 5.5 by 0.152
Claude Sonnet 5.5 vs Claude Opus 4.7
0.692 vs 0.519 · Claude Sonnet 5.5 by 0.173
Claude Sonnet 5.5 vs GPT-5.5
0.692 vs 0.518 · Claude Sonnet 5.5 by 0.174
Claude Sonnet 5.5 vs Grok 4.6
0.692 vs 0.485 · Claude Sonnet 5.5 by 0.207
Claude Sonnet 5.5 vs GPT-5.4
0.692 vs 0.481 · Claude Sonnet 5.5 by 0.211
Claude Sonnet 5.5 vs GPT-5
0.692 vs 0.462 · Claude Sonnet 5.5 by 0.230
Claude Sonnet 5.5 vs GPT-5.2
0.692 vs 0.459 · Claude Sonnet 5.5 by 0.233
Claude Sonnet 5.5 vs Claude Sonnet 4.6
0.692 vs 0.442 · Claude Sonnet 5.5 by 0.250
Claude Sonnet 5.5 vs GPT-5.6 Luna (August)
0.692 vs 0.441 · Claude Sonnet 5.5 by 0.251
Claude Sonnet 5.5 vs GPT-5.1
0.692 vs 0.396 · Claude Sonnet 5.5 by 0.296
Claude Sonnet 5.5 vs GPT-5.5 Instant
0.692 vs 0.384 · Claude Sonnet 5.5 by 0.308
Claude Sonnet 5.5 vs MAI-Thinking-1
0.692 vs 0.350 · Claude Sonnet 5.5 by 0.342

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