WHBench: leaderboard
Open-ended women's health questions from WHBench (2026): 47 clinician-designed scenarios in ten topics, each built around a typical LLM failure mode such as outdated guidelines, dosage errors or missed health disparities. A Claude Sonnet 4.6 judge grades each answer against four to six independent clinician reference answers with a 23-criterion rubric that penalizes unsafe advice heavily, and the score is the mean normalized rubric score in percent; higher is better.
Metric: Mean normalized rubric score (%), the raw score from -58 to +92 mapped to 0-100 on the 47 expert-written WHBench scenarios in ten women's health topics (fertility, hormonal health, pregnancy, PCOS, contraception and others), three runs per question at temperature 0 with a 4,096-token cap, each response graded by a Claude Sonnet 4.6 judge against 4-6 clinician reference answers and a 23-criterion rubric with asymmetric safety penalties; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 22 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 72.1 | #113 |
| 2 | Claude Sonnet 4.6 | 67.1 | #173 |
| 3 | GPT-5.4 | 66.8 | #135 |
| 4 | Gemini 3 Flash (Preview) | 64.7 | #152 |
| 5 | O3 | 63.6 | #237 |
| 6 | DeepSeek V3.2 | 61.3 | #419 |
| 7 | Grok 3 | 60.7 | #611 |
| 8 | Mistral Large 3 | 60.2 | #832 |
| 9 | Grok 4 | 57.9 | #319 |
| 10 | DeepSeek R1 | 52.9 | #482 |
| 11 | GPT-4.1 | 51.8 | #505 |
| 12 | Grok 3 Mini | 50 | #565 |
| 13 | Gemini 2.5 Flash | 49.5 | #463 |
| 14 | Claude Opus 4 | 49.1 | #326 |
| 15 | Claude Sonnet 4 | 48.1 | #410 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=whbench · How It Works · Data refreshed daily, snapshot 2026-11-21.