Clinical Verbatim Citation - Claim Support (Strict): leaderboard
Metric: Fully supported cited claims (%, judge deepseek-v4-flash). Source: arxiv.org. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 79 |
| 2 | GPT-5.4 | 76.9 |
| 3 | DeepSeek V4 Pro | 73.8 |
| 4 | GPT-5.4 Mini | 62.4 |
| 5 | DeepSeek V4 Flash | 60.5 |
| 6 | Claude Haiku 4.5 | 44.1 |
| 7 | GLM-5.2 | 40.3 |
| 8 | Claude Sonnet 5 | 38.5 |
| 9 | GLM-4.7 Flash | 38.2 |
| 10 | Claude Opus 5 | 37.8 |
| 11 | GPT-4.1 Mini | 36.2 |
| 12 | Kimi K3 | 33.8 |
Interactive version: theaggregate.ai/benchmark?slug=clinical-verbatim-citation-claim-support-strict · How It Works · Data refreshed daily, snapshot 2026-09-20.