Benchmark
BabyVision Benchmark
What is BabyVision?
A benchmark for early-stage visual reasoning and perception on child-like vision tasks. Benchmark Radar tracks 10 reported scores for BabyVision, cited by 1…
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 10
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/babyvision?top_n=500
BabyVision results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Kimi K2.6 | Moonshot AI | 0.685 | 2026-04-20 | evidence |
| Kimi K3 | Moonshot AI | 0.857 | 2026-07-16 | evidence |
| Muse Spark 1.1 | Meta | 0.763 | 2026-07-09 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.402 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.446 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.384 | 2026-02-24 | evidence |
| Qwen3.7-Plus | Qwen | 0.704 | 2026-05-31 | evidence |
| Qwen3.8-27B | Qwen | 0.856 | 2026-08-14 | evidence |
| Seed 2.1 Pro | ByteDance | 0.737 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.629 | 2026-06-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.