Claude Opus 5 on HealthBench Professional

rank 11 of 31 · updated September 30, 2026

Claude Opus 5 scores 0.598 on HealthBench Professional, rank 11 of 31 models on the board. Anthropic's frontier workhorse, priced at half of Claude Fable 5. 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	11 of 31
score	0.598
lab	Anthropic
context window	1.0M tokens
API price per 1M tokens	$5.00 in / $25.00 out
license	proprietary
source	System Card: Claude Opus 5 (system card)
released	2026-07-24

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.105. Directly above sits GPT-5.6 Sol at 0.605. Directly below sits Muse Spark 1.1 at 0.593. 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 5 (system card, Anthropic, 2026-07-24). Vendor-reported. Confidence: verified. Configuration: length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%)..

Claude Opus 5 achieved a raw score of 73.4%, which is the highest amongst all Claude models, ahead of Claude Mythos 5 at 70.3%, Claude Opus 4.8 at 60.3%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 59.8%.

p. 189, section 8.15.2 HealthBench Professional results; also Table 8.1.A p. 152 ('HealthBench Professional 59.8 ...') · 1 corroborating document · full entry on the sources page

What does Claude Opus 5 score on HealthBench Professional?

Claude Opus 5 scores 0.598 on HealthBench Professional, which places it at rank 11 of 31 models on the board as of September 30, 2026. The number was read from System Card: Claude Opus 5, listed on the sources page.

How much does Claude Opus 5 cost to run?

Claude Opus 5 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 5 vs GPT-6 Astra (Anthropic run)
0.598 vs 0.703 · GPT-6 Astra (Anthropic run) by 0.105
Claude Opus 5 vs Claude Sonnet 5.5
0.598 vs 0.692 · Claude Sonnet 5.5 by 0.094
Claude Opus 5 vs Claude Fable 5
0.598 vs 0.660 · Claude Fable 5 by 0.062
Claude Opus 5 vs Claude Opus 5.5
0.598 vs 0.656 · Claude Opus 5.5 by 0.058
Claude Opus 5 vs GPT-6 Astra
0.598 vs 0.647 · GPT-6 Astra by 0.049
Claude Opus 5 vs Claude Fable 5 (September card)
0.598 vs 0.633 · Claude Fable 5 (September card) by 0.035
Claude Opus 5 vs Claude Fable 5.1
0.598 vs 0.621 · Claude Fable 5.1 by 0.023
Claude Opus 5 vs GPT-6 Luna
0.598 vs 0.608 · GPT-6 Luna by 0.010
Claude Opus 5 vs GPT-6 Sol
0.598 vs 0.608 · GPT-6 Sol by 0.010
Claude Opus 5 vs GPT-5.6 Sol
0.598 vs 0.605 · GPT-5.6 Sol by 0.007
Claude Opus 5 vs Muse Spark 1.1
0.598 vs 0.593 · Claude Opus 5 by 0.005
Claude Opus 5 vs Claude Sonnet 5
0.598 vs 0.578 · Claude Opus 5 by 0.020
Claude Opus 5 vs GPT-5.6 Terra
0.598 vs 0.577 · Claude Opus 5 by 0.021
Claude Opus 5 vs Claude Opus 4.8 (Opus 4.8 grader)
0.598 vs 0.574 · Claude Opus 5 by 0.024
Claude Opus 5 vs Grok 4.7
0.598 vs 0.567 · Claude Opus 5 by 0.031
Claude Opus 5 vs Claude Opus 4.8
0.598 vs 0.558 · Claude Opus 5 by 0.040
Claude Opus 5 vs GPT-5.6 Luna
0.598 vs 0.557 · Claude Opus 5 by 0.041
Claude Opus 5 vs Muse Spark
0.598 vs 0.541 · Claude Opus 5 by 0.057
Claude Opus 5 vs GPT-5.6 Sol (August)
0.598 vs 0.540 · Claude Opus 5 by 0.058
Claude Opus 5 vs Claude Opus 4.7
0.598 vs 0.519 · Claude Opus 5 by 0.079
Claude Opus 5 vs GPT-5.5
0.598 vs 0.518 · Claude Opus 5 by 0.080
Claude Opus 5 vs Grok 4.6
0.598 vs 0.485 · Claude Opus 5 by 0.113
Claude Opus 5 vs GPT-5.4
0.598 vs 0.481 · Claude Opus 5 by 0.117
Claude Opus 5 vs GPT-5
0.598 vs 0.462 · Claude Opus 5 by 0.136
Claude Opus 5 vs GPT-5.2
0.598 vs 0.459 · Claude Opus 5 by 0.139
Claude Opus 5 vs Claude Sonnet 4.6
0.598 vs 0.442 · Claude Opus 5 by 0.156
Claude Opus 5 vs GPT-5.6 Luna (August)
0.598 vs 0.441 · Claude Opus 5 by 0.157
Claude Opus 5 vs GPT-5.1
0.598 vs 0.396 · Claude Opus 5 by 0.202
Claude Opus 5 vs GPT-5.5 Instant
0.598 vs 0.384 · Claude Opus 5 by 0.214
Claude Opus 5 vs MAI-Thinking-1
0.598 vs 0.350 · Claude Opus 5 by 0.248

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