HealthBenchBrowse 284 families
HealthBench
Can the model produce useful work in a professional knowledge-work setting?
- Domain
- Knowledge Work
- Ranked models
- 7
- Reported values
- 7
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Latest stable
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | GPT-6 AstraOpenAI | reportedcost n/a1 value · Sep 3 · source | 58.3% |
| 2 | GPT-5.6 SolOpenAI | reportedcost n/a1 value · Sep 3 · source | 57.0% |
| 3 | GPT-5.6 TerraOpenAI | reportedcost n/a1 value · Sep 3 · source | 57.0% |
| 4 | GPT-5.5OpenAI | reportedcost n/a1 value · Sep 3 · source | 56.5% |
| 5 | GPT-5.6 LunaOpenAI | reportedcost n/a1 value · Sep 3 · source | 55.8% |
| 6 | GPT-6 LunaOpenAI | reportedcost n/a1 value · Sep 22 · source | 54.5% |
| 7 | GPT-6 SolOpenAI | reportedcost n/a1 value · Sep 22 · source | 53.2% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
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. Length-adjusted score on the 0-100 scale reported by OpenAI.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
OpenAI's September 22 appendix corrects the earlier Astra value to 58.3. The table prints length-adjusted score followed by unadjusted score and mean response length in characters: GPT-6 Astra 58.3 (60.8, 977); GPT-6 Sol 53.2 (47.1, 977); GPT-6 Luna 54.5 (50.0, 1255). Earlier GPT-5.5 and GPT-5.6 comparison values are retained from the same report: 56.5 (58.4, 2313); 57.0 (55.6, 1764); 57.0 (58.7, 2285); 55.8 (55.4, 1930).
Method / source ↗