VRIQ (Natural): leaderboard
Metric: Mean accuracy (%) over the five natural-domain VRIQ categories (500 puzzles over real-world objects and scenes, 100 per category; figure rotation is three-option, the rest four-option); higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 54.2 | #333 |
| 2 | Gemini 2.5 Pro | 53.6 | #145 |
| 3 | GPT-5.1 | 51.8 | #131 |
| 4 | Qwen 3 VL 32B (Thinking) | 47.2 | #287 (Qwen 3 VL 32B) |
| 5 | GPT-4o Mini | 43.8 | #588 |
| 6 | GPT-5 Mini | 43.2 | #176 |
| 7 | Qwen 2.5 VL 7B Instruct | 30 | #643 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=vriq-natural · How It Works · Data refreshed daily, snapshot 2026-10-11.