V-DyKnow - Visual Entity Recognition: leaderboard
Metric: Accuracy (%) of naming the entity depicted in each V-DyKnow image (country flag and coat of arms, athlete portrait, organization logo) for the 139 facts' entities, best of three prompt variants (upper bound); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 VL 7B Instruct | 91 | #816 |
| 2 | Qwen 2.5 VL 7B Instruct | 87 | #643 |
| 3 | GPT-4.1 | 83 | #240 |
| 4 | GPT-5.1 (2025-11-13) | 75 | #97 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=v-dyknow-visual-entity-recognition · How It Works · Data refreshed daily, snapshot 2026-10-11.