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

#ModelScoreOverall rank
1Gemini 2.5 Pro51.8#280
2Qwen 2.5 VL 32B Instruct49.5#1065
3O343.1#242
4GT-Thinker-7B39.6
5Vision-G1-7B38.1
6Qwen 2.5 VL 7B Instruct36.4#1919
7GPT-4o35#754
8V-Thinker-8B (MindsEye checkpoint unspecified)32.2
9PaliGemma-3B (MindsEye checkpoint unspecified)29.6
10llava-v1.6-mistral-7B29.1#4027
11Phi-3.5-Vision Instruct (MindsEye checkpoint unspecified)28.7
12SmolVLM-2.2B (MindsEye checkpoint unspecified)28.2
13Llama 3.2 11B Vision28#4281
14MindsEye InternVL3-8B (checkpoint unspecified)28
15Qwen 2.5 VL 3B Instruct27.9#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.