BabyVision — leaderboard
Visual reasoning tasks that 3-year-old children can solve - fine-grained discrimination, visual tracking, spatial perception, and pattern recognition. 388 questions across 22 subtypes. Human baseline: 94.1%.
Metric: Score (%). Source: unipat.ai. Status: saturation imminent. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | Median Human | 94.1 |
| 3 | GPT-5.5 | 83.6 |
| 4 | Claude 3 Opus | 81.2 |
| 5 | Seed 2.1 Pro | 73.7 |
| 6 | Kimi K2.6 | 68.5 |
| 7 | Gemini 3.1 Pro (Preview) | 51.6 |
| 8 | Gemini 3 Pro | 49.7 |
| 9 | GPT-5.4 (xHigh) | 49.7 |
| 10 | Qwen 3.5 397B A17B | 43.3 |
| 11 | Kimi K2.5 | 36.5 |
| 12 | GPT-5.2 | 34.4 |
| 13 | Seed 1.8 | 30.2 |
| 14 | Qwen 3 VL 235B A22B (Thinking) | 22.2 |
| 15 | GLM-4.6V | 17.6 |
Interactive version: theaggregate.ai/benchmark?slug=babyvision · How the rankings work · Data refreshed daily, snapshot 2026-07-22.