Skip to main content
BenchLM

HealthBench Hard

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

A harder subset of OpenAI's HealthBench for evaluating open-ended medical and health reasoning with rubric-based grading.

Benchmark score on HealthBench Hard — September 27, 2026

We compile the HealthBench Hard rows from provider self-reports and secondary reports. Muse Spark leads the table at 42.8%, followed by GPT-5.4 (40.1%) and GPT-6 Astra (36.6%). We do not use these results to rank models overall.

11 modelsKnowledgeCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (11 models)

Score
1
Muse SparkMeta · Closed
42.8%
2
GPT-5.4OpenAI · Closed
40.1%
3
GPT-6 AstraOpenAI · Closed
36.6%
4
GPT-5.6 SolOpenAI · Closed
33.1%
5
GPT-5.6 TerraOpenAI · Closed
32.7%
6
GPT-5.6 LunaOpenAI · Closed
32.0%
7
GPT-6 LunaOpenAI · Closed
31.4%
8
GPT-6 SolOpenAI · Closed
30.1%
9
Gemini 3.1 ProGoogle · Closed
20.6%
10
Grok 4.20xAI · Closed
20.3%
11
Claude Opus 4.6Anthropic · Closed
14.8%

Among the reported HealthBench Hard rows, Muse Spark is first at 42.8%. The third row is 6.2 points behind. The broader top-10 range is 22.5 points, so the table still separates the published systems.

11 models have been evaluated on HealthBench Hard. The benchmark falls in the Knowledge category. HealthBench Hard is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About HealthBench Hard

Year

2026

Tasks

1,000 health prompts

Format

Open-ended health evaluation

Difficulty

Advanced health reasoning

Meta describes HealthBench Hard as a 1,000-prompt subset of OpenAI's HealthBench, graded with the same simple-evals implementation and a GPT-4.1-based judge. BenchLM treats it as a display-only health benchmark reference.

Freshness and provenance

Version

HealthBench Hard 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does HealthBench Hard measure?

A harder subset of OpenAI's HealthBench for evaluating open-ended medical and health reasoning with rubric-based grading.

Which model scores highest on HealthBench Hard?

Muse Spark by Meta currently leads with a score of 42.8% on HealthBench Hard.

How many models are evaluated on HealthBench Hard?

11 AI models have been evaluated on HealthBench Hard on BenchLM.

Last updated: September 27, 2026 · BenchLM version HealthBench Hard 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.