Mind's Eye - Visual Relation Abstraction: 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 a Bongard-style task of finding the figure that lacks the attribute the others share; higher is better.
Metric: Accuracy (%) on the visual relation abstraction (Bongard-style, find the figure lacking the shared attribute) task of Mind's Eye (6-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 | 29 | #276 |
| 2 | GPT-4o | 28.4 | #751 |
| 3 | Qwen 2.5 VL 32B Instruct | 25.1 | #1062 |
| 4 | Idefics-8B (MindsEye checkpoint unspecified) | 24 | |
| 5 | GT-Thinker-7B | 23.1 | |
| 6 | Vision-G1-7B | 22.3 | |
| 7 | Llama 3.2 11B Vision | 22 | #4264 |
| 8 | MindsEye InternVL3-8B (checkpoint unspecified) | 22 | |
| 9 | Phi-3.5-Vision Instruct (MindsEye checkpoint unspecified) | 22 | |
| 10 | V-Thinker-8B (MindsEye checkpoint unspecified) | 21.5 | |
| 11 | O3 | 21.1 | #237 |
| 12 | Qwen 2.5 VL 3B Instruct | 20 | #2713 |
| 13 | Qwen 2.5 VL 7B Instruct | 19.1 | #1902 |
| 14 | InstructBLIP-4B (MindsEye checkpoint unspecified) | 16.3 | |
| 15 | llava-v1.6-mistral-7B | 16 | #3999 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mind-s-eye-visual-relation-abstraction · How It Works · Data refreshed daily, snapshot 2026-11-21.