Cited but Not Verified — leaderboard
Metric: Relevant Content (self-reported). Source: benchmarklist.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 95.7 |
| 2 | GPT-5.4 | 93.7 |
| 3 | GPT-5.2 | 92.3 |
| 4 | Claude Haiku 4.5 | 91.1 |
| 5 | Claude Sonnet 4.6 | 89.8 |
| 6 | Claude Sonnet 4.5 | 88.3 |
| 7 | GPT-5 Mini | 87.4 |
| 8 | Claude Opus 4.6 | 83.9 |
| 9 | Gemini 3 Flash (Preview) | 82.9 |
| 10 | Gemini 3.1 Pro (Preview) | 80.7 |
| 11 | Pixtral Large | 64.9 |
| 12 | Llama 4 Maverick | 60.6 |
Interactive version: theaggregate.ai/benchmark?slug=cited-but-not-verified · How the rankings work · Data refreshed daily, snapshot 2026-07-22.