Visual reasoning

BabyVision

Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better.

Rankings

Higher is better

BabyVision — frequently asked questions

What is BabyVision?
Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better.
Which AI model scores highest on BabyVision?
Qwen3.8-Max by Qwen holds the best BabyVision result among tracked models, at 82% (released Aug 3 2026). Higher scores are better on this benchmark.
What are the top 3 models on BabyVision?
1. Qwen3.8-Max (Qwen) — 82%; 2. Muse Spark 1.1 (Meta) — 76.3%; 3. Muse Spark (Meta) — 39.9%.
How many models have a published BabyVision score?
3 tracked models have a published BabyVision score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.