Mind's Eye - Mental Composition: leaderboard
Mind's Eye (2026) is a multiple-choice benchmark of visuospatial reasoning tasks adapted from human intelligence tests, with procedurally generated items answered with chain-of-thought prompting. This board is accuracy in percent on matching a flat net to the solid it folds into; higher is better.
Metric: Accuracy (%) on the mental composition (net to solid) task of Mind's Eye (4-option multiple choice, 100 procedurally generated items, chain-of-thought prompt, answers extracted by an LLM evaluator; keys uniformly distributed over the options); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 51.8 | #280 |
| 2 | Qwen 2.5 VL 32B Instruct | 49.5 | #1065 |
| 3 | O3 | 43.1 | #242 |
| 4 | GT-Thinker-7B | 39.6 | |
| 5 | Vision-G1-7B | 38.1 | |
| 6 | Qwen 2.5 VL 7B Instruct | 36.4 | #1919 |
| 7 | GPT-4o | 35 | #754 |
| 8 | V-Thinker-8B (MindsEye checkpoint unspecified) | 32.2 | |
| 9 | PaliGemma-3B (MindsEye checkpoint unspecified) | 29.6 | |
| 10 | llava-v1.6-mistral-7B | 29.1 | #4027 |
| 11 | Phi-3.5-Vision Instruct (MindsEye checkpoint unspecified) | 28.7 | |
| 12 | SmolVLM-2.2B (MindsEye checkpoint unspecified) | 28.2 | |
| 13 | Llama 3.2 11B Vision | 28 | #4281 |
| 14 | MindsEye InternVL3-8B (checkpoint unspecified) | 28 | |
| 15 | Qwen 2.5 VL 3B Instruct | 27.9 | #2720 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mind-s-eye-mental-composition · How It Works · Data refreshed daily, snapshot 2026-11-22.