Clinical Benchmarks

Anthropic logoClaude Fable 5: healthcare benchmark results

Anthropic · 4 boards · updated August 16, 2026

The index currently holds 4 results for Claude Fable 5: 0.660 on HealthBench Professional (1 of 9), 83.8 on Health Optimization Bench (1 of 15), 56.07% on MedCode (Vals AI) (3 of 85), ~90 on MedScribe (Vals AI) (4 of 84). It tops HealthBench Professional and Health Optimization Bench. Scores below sit on different scales and come from different graders, so read each against its own benchmark, never against the others.

Results by benchmark

benchmarkscorepositionas of
HealthBench Professional
via healthbenchprofessional.com
0.6601 of 92026-08
Health Optimization Bench
via healthoptimizationbench.com
83.81 of 152026-08
MedCode (Vals AI)
via Vals AI MedCode leaderboard
56.07%3 of 852026-08
MedScribe (Vals AI)
via Vals AI MedScribe leaderboard
~904 of 842026-08

Position counts against the source's full board, including rows this index does not mirror. Config caveats, where a source noted any, are on each benchmark's page.

Which healthcare benchmarks is Claude Fable 5 scored on?

As of August 16, 2026, Claude Fable 5 holds current results on 4 tracked benchmarks: HealthBench Professional, Health Optimization Bench, MedCode (Vals AI), MedScribe (Vals AI).

How does Claude Fable 5 rank on them?

Claude Fable 5 stands at 0.660 on HealthBench Professional (1 of 9), 83.8 on Health Optimization Bench (1 of 15), 56.07% on MedCode (Vals AI) (3 of 85), ~90 on MedScribe (Vals AI) (4 of 84). It holds first place on HealthBench Professional and Health Optimization Bench.

The benchmarks themselves are described on their pages, linked in the table above, and the whole field is on the index.