WHBench: leaderboard
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 January 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 72.1 |
| 2 | Claude Sonnet 4.6 | 67.1 |
| 3 | GPT-5.4 | 66.8 |
| 4 | Gemini 3 Flash (Preview) | 64.7 |
| 5 | O3 | 63.6 |
| 6 | DeepSeek V3.2 | 61.3 |
| 7 | Grok 3 | 60.7 |
| 8 | Mistral Large 3 | 60.2 |
| 9 | Grok 4 | 57.9 |
| 10 | DeepSeek R1 | 52.9 |
| 11 | GPT-4.1 | 51.8 |
| 12 | Grok 3 Mini | 50 |
| 13 | Gemini 2.5 Flash | 49.5 |
| 14 | Claude Opus 4 | 49.1 |
| 15 | Claude Sonnet 4 | 48.1 |
Interactive version: theaggregate.ai/benchmark?slug=whbench · How It Works · Data refreshed daily, snapshot 2026-10-07.