HealthBench Hard
Can the model produce useful work in a professional knowledge-work setting?
Knowledge Work4 ranked models4 reported values1 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | GPT-5.6 SolOpenAI | 31.4% | Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source |
| 2 | GPT-5.6 LunaOpenAI | 28.7% | Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source |
| 3 | GPT-5.5OpenAI | 22.9% | Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source |
| 4 | GPT-5.3 InstantOpenAI | 20.2% | Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model produce useful work in a professional knowledge-work setting?
Professional analysis, document, finance, office, or domain-specific tasks. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
The score is length-adjusted; source also prints unadjusted score and mean response length: 17.8/1,693; 21.3/1,794; 27.1/1,450; 24.9/1,523.
Method / source