multimodal benchmark
BabyVision Leaderboard
BabyVision is a multimodal benchmark for early-stage visual reasoning and perception on child-like vision tasks.
Updated Sep 5, 2026
Models11
Model coverage11
MetricScore
EvidenceB
BabyVision Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score85.70% | Percentile100.00% | Participants11 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score85.60% | Percentile90.00% | Participants11 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score76.30% | Percentile80.00% | Participants11 | EvidenceC | Evaluated |
| Rank04 | ModelBY | Score73.70% | Percentile70.00% | Participants11 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score70.40% | Percentile60.00% | Participants11 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score68.50% | Percentile50.00% | Participants11 | EvidenceC | Evaluated |
| Rank07 | ModelBY | Score62.90% | Percentile40.00% | Participants11 | EvidenceC | Evaluated |
| Rank08 | ModelZA | Score53.40% | Percentile30.00% | Participants11 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score44.60% | Percentile20.00% | Participants11 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score40.20% | Percentile10.00% | Participants11 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score38.40% | Percentile0.00% | Participants11 | EvidenceC | Evaluated |
BabyVision Highlights
The leading models and scores on this benchmark.
BabyVision Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BabyVision
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BabyVision?
What BabyVision measures and how its scores work.
BabyVision is a multimodal benchmark for child-like vision tasks.
It measures early-stage visual reasoning and perception using the Score metric, reported as a ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 85.70%.
What are the top three models on BabyVision?
The current leaders are Kimi K3 (85.70%), Qwen3.8-27B (85.60%), and Muse Spark 1.1 (76.30%).
Which BabyVision model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.08 input / $0.25 output per 1M tokens.
Which models are fastest among BabyVision results?
The fastest matched records are GLM-5.3-Flash (74.28 tok/s via FriendliAI), Muse Spark 1.1 (14.00 tok/s via Meta Model API), and Kimi K2.6 (1.24 tok/s via Moonshot AI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.