Health AI Benchmarks

Claude Opus 5

6 results on 5 boards

Made by
Anthropic
Released
24 July 2026
Licence
proprietary
Context
1.0M
Input, per 1M tokens
$5
Output, per 1M tokens
$25

Health Evals Index

63.1rank 4 of 533 of 4 boards

This site's own calculation from 3 of 4 benchmarks. How it works

How this score is made
  • HealthBench Professional0.59859.8 out of 100runs −2.5 hardadjusted 62.3weight 0.446, supportingsystem cardReported by the maker.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%).
  • HealthBench67.167.1 out of 100runs −0.5 leveladjusted 67.6weight 0.798, coresystem cardReported by the maker.raw/unadjusted, Anthropic system-card protocol (max effort, no tools, five trials); length-adjusted 57.8; mirrored on benchlm.ai
  • Health Optimization Bench: incretin78.378.3 out of 100runs +4.0 easyadjusted 74.3weight 0.226, supportingofficial leaderboardNear its ceiling (leader 84.9), so it counts for less.
  • SAFE-TeenNo result here, and none is filled in.
Adjusted average of 3 benchmarks, by weight
67.0
Field average, counts for 33.3% with 3 of 4 benchmarks
55.3
Index
= 63.1

Runs: how far that benchmark's scores sit above or below the same models' scores on the others. Adjusted: the score minus that amount. The fewer benchmarks behind a score, the more the field average counts.

Benchmark by benchmark

Claude Opus 5 next to the top 10 on each benchmark it has a score on, on that benchmark's own scale. Its own column is in colour.

Every result, with its source

Each against its own board only. The dot strip shows the whole board; this model is the larger red dot.

Compare Claude Opus 5 with other models