ClinConsensus - Lay-Facing: leaderboard
Metric: CACS@10 (%; GPT-5.1 rubric judge, lay-facing cases). Source: arxiv.org. Saturation forecast: Around 2029. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (High) | 33.9 |
| 2 | Qwen 3.5 Plus | 26.1 |
| 3 | Claude Opus 4.6 | 25.2 |
| 4 | Kimi K2.5 | 23 |
| 5 | DeepSeek V3.2 | 22.9 |
| 6 | Qwen 3 Max (2026-01-23) | 22.3 |
| 7 | Gemini 3.1 Pro (Preview) | 22 |
| 8 | Grok 4.1 Fast | 19.9 |
| 9 | Seed 2.0 Pro | 19.9 |
| 10 | GLM-5 | 19.5 |
Interactive version: theaggregate.ai/benchmark?slug=clinconsensus-lay-facing · How It Works · Data refreshed daily, snapshot 2026-09-25.