PosterIQ: leaderboard
Metric: Understanding average (x 100, from -20 to 100): mean of the OCR, font, layout, design-understanding and rating-alignment group scores on PosterIQ's poster-understanding tasks (7,765 instances from real, professional and synthetic posters), each group score being the mean of its positively oriented metrics; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 64.7 | #145 |
| 2 | GPT-5 | 62.2 | #91 |
| 3 | Claude Sonnet 4.5 | 60.1 | #138 |
| 4 | Gemma 3n E4B (IT) | 48.6 | #736 |
| 5 | Grok 4 Fast | 47.1 | #242 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=posteriq · How It Works · Data refreshed daily, snapshot 2026-10-11.