PosterIQ - Rating Alignment: leaderboard
Metric: Rating alignment (x 100, from -100 to 100): cosine similarity between the model's normalized 0-10 quality ratings of 219 posters and the normalized human ratings; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3n E4B (IT) | 48.3 | #736 |
| 2 | Grok 4 Fast | 46.5 | #242 |
| 3 | Gemini 2.5 Pro | 39.9 | #145 |
| 4 | Claude Sonnet 4.5 | 38.4 | #138 |
| 5 | GPT-5 | 34.7 | #91 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=posteriq-rating-alignment · How It Works · Data refreshed daily, snapshot 2026-10-11.