multimodal benchmark
BabyVision
A benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Updated Aug 7, 2026
Published models9
Registry coverage9
MetricScore
EvidenceB
BabyVision leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 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 |
Score distribution
Top published rows on the benchmark's original scale.
BabyVision highlights
The top published results on this benchmark's own scale.
What is BabyVision?
Definition and scoring fields from the benchmark registry.
A benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- BabyVision
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- babyvision|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.