multimodal benchmark
BabyVision
A benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Updated Aug 11, 2026
Models9
Model coverage9
MetricScore
EvidenceB
BabyVision Ranking
Higher score ranks better on this benchmark.
| 1 | MA | 85.7% | 100.0% | 9 | C | |
| 2 | ME | 76.3% | 87.5% | 9 | C | |
| 3 | BY | 73.7% | 75.0% | 9 | C | |
| 4 | AC | 70.4% | 62.5% | 9 | C | |
| 5 | MA | 68.5% | 50.0% | 9 | C | |
| 6 | BY | 62.9% | 37.5% | 9 | C | |
| 7 | AC | 44.6% | 25.0% | 9 | C | |
| 8 | AC | 40.2% | 12.5% | 9 | C | |
| 9 | AC | 38.4% | 0.0% | 9 | C |
BabyVision Score Distribution
A closer view of the leading scores on this benchmark.
BabyVision Highlights
The leading models and scores on this benchmark.
What is BabyVision?
What BabyVision measures and how its scores work.
A benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BabyVision
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- babyvision|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BabyVision.
Which model scores highest on BabyVision?
Kimi K3 is currently ranked first with 85.7%.
What does BabyVision measure?
A benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
9 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.