Claude Opus 4.7 on HealthBench Professional

rank 13 of 22 · updated September 8, 2026

Claude Opus 4.7 scores 0.519 on HealthBench Professional, rank 13 of 22 models on the board. Anthropic's April 2026 Opus release, superseded by Opus 4.8 six weeks later at the same price. 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	13 of 22
score	0.519
lab	Anthropic
context window	1M tokens
API price per 1M tokens	$5.00 in / $25.00 out
license	proprietary
source	System Card: Claude Opus 4.8 (system card)
released	2026-04-16

Position in the field

The gap to the leader, Claude Fable 5 at 0.660, is 0.141. Directly above sits GPT-5.6 Sol (August) at 0.540. Directly below sits GPT-5.5 at 0.518. 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 System Card: Claude Opus 4.8 (system card, Anthropic, 2026-05-28). Vendor-reported. Confidence: verified. Configuration: length-adjusted; adaptive thinking at max effort; Claude Sonnet 4.6 grader; 5 trials; comparison model in the Opus 4.8 card.

Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%.

p. 228, section 8.14.1 HealthBench Professional; Figure 8.14.A p. 229 · full entry on the sources page

What does Claude Opus 4.7 score on HealthBench Professional?

Claude Opus 4.7 scores 0.519 on HealthBench Professional, which places it at rank 13 of 22 models on the board as of September 8, 2026. The number was read from System Card: Claude Opus 4.8, listed on the sources page.

How much does Claude Opus 4.7 cost to run?

Claude Opus 4.7 is priced at $5.00 per million input tokens and $25.00 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 Opus 4.7 vs Claude Fable 5
0.519 vs 0.660 · Claude Fable 5 by 0.141
Claude Opus 4.7 vs GPT-6 Astra
0.519 vs 0.634 · GPT-6 Astra by 0.115
Claude Opus 4.7 vs Claude Fable 5.1
0.519 vs 0.621 · Claude Fable 5.1 by 0.102
Claude Opus 4.7 vs GPT-5.6 Sol
0.519 vs 0.605 · GPT-5.6 Sol by 0.086
Claude Opus 4.7 vs Claude Opus 5
0.519 vs 0.598 · Claude Opus 5 by 0.079
Claude Opus 4.7 vs Muse Spark 1.1
0.519 vs 0.593 · Muse Spark 1.1 by 0.074
Claude Opus 4.7 vs Claude Sonnet 5
0.519 vs 0.578 · Claude Sonnet 5 by 0.059
Claude Opus 4.7 vs GPT-5.6 Terra
0.519 vs 0.577 · GPT-5.6 Terra by 0.058
Claude Opus 4.7 vs Claude Opus 4.8
0.519 vs 0.558 · Claude Opus 4.8 by 0.039
Claude Opus 4.7 vs GPT-5.6 Luna
0.519 vs 0.557 · GPT-5.6 Luna by 0.038
Claude Opus 4.7 vs Muse Spark
0.519 vs 0.541 · Muse Spark by 0.022
Claude Opus 4.7 vs GPT-5.6 Sol (August)
0.519 vs 0.540 · GPT-5.6 Sol (August) by 0.021
Claude Opus 4.7 vs GPT-5.5
0.519 vs 0.518 · Claude Opus 4.7 by 0.001
Claude Opus 4.7 vs GPT-5.4
0.519 vs 0.481 · Claude Opus 4.7 by 0.038
Claude Opus 4.7 vs GPT-5
0.519 vs 0.462 · Claude Opus 4.7 by 0.057
Claude Opus 4.7 vs GPT-5.2
0.519 vs 0.459 · Claude Opus 4.7 by 0.060
Claude Opus 4.7 vs Claude Sonnet 4.6
0.519 vs 0.442 · Claude Opus 4.7 by 0.077
Claude Opus 4.7 vs GPT-5.6 Luna (August)
0.519 vs 0.441 · Claude Opus 4.7 by 0.078
Claude Opus 4.7 vs GPT-5.1
0.519 vs 0.396 · Claude Opus 4.7 by 0.123
Claude Opus 4.7 vs GPT-5.5 Instant
0.519 vs 0.384 · Claude Opus 4.7 by 0.135
Claude Opus 4.7 vs MAI-Thinking-1
0.519 vs 0.350 · Claude Opus 4.7 by 0.169

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