HealthBench Professional
Can the model produce useful work in a professional knowledge-work setting?
Knowledge Work8 ranked models10 reported values3 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 | Claude Mythos PreviewAnthropic | 64.7% | Reported configurationAnthropic report1 value · 1 reportJun 9, 2026 · source |
| 2 | Claude Fable 5Anthropic | 60.9% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 3 | GPT-5.6 SolOpenAI | 60.5% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 4 | GPT-5.6 TerraOpenAI | 57.7% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 5 | Claude Opus 4.8Anthropic | 56.9% | Reported configurationAnthropic report2 values · 2 reportsJun 9, 2026 · source |
| 6 | Grok 4.7SpaceXAI | 56.7% | xhigh effortSpaceXAI report1 value · 1 reportSep 21, 2026 · source |
| 7 | GPT-5.6 LunaOpenAI | 55.7% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 8 | GPT-5.5OpenAI | 51.8% | Reported configurationAnthropic report2 values · 2 reportsJun 9, 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.
SpaceXAI reports 56.7% for Grok 4.7 at xhigh; the table does not print the benchmark harness or task revision.
Method / source