HealthBench Professional
Task evaluation for medical professionals. Whether length adjustment was used is not stated in the source.
- Category
- Knowledge
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- All model rankings (records) · Ranked results: 2
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 2)
official results (Grok 4.7 (xAI news))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Grok 4.7 | Xhigh | 56.7% | — | xAI | Grok 4.7 (xAI news)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)Source excerptHealthBench Professional | Grok 4.7 (xHigh) 56.7 |
| 2 | Grok 4.6 | High | 48.5% | — | xAI | Grok 4.7 (xAI news)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by xAI (comparison column on the Grok 4.7 announcement page)Source excerptHealthBench Professional | Grok 4.6 (High) 48.5 |