Benchmark

BabyVision

A benchmark for early-stage visual reasoning and perception on child-like vision tasks.

Modality
multimodal
Categories
multimodal, reasoning, vision
Openness
unknown
Source
llm_stats
Reported scores
10

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Kimi K2.6Moonshot AI0.6852026-04-20evidence
Kimi K3Moonshot AI0.8572026-07-16evidence
Muse Spark 1.1Meta0.7632026-07-09evidence
Qwen3.5-122B-A10BQwen0.4022026-02-24evidence
Qwen3.5-27BQwen0.4462026-02-24evidence
Qwen3.5-35B-A3BQwen0.3842026-02-24evidence
Qwen3.7-PlusQwen0.7042026-05-31evidence
Qwen3.8-27BQwen0.8562026-08-14evidence
Seed 2.1 ProByteDance0.7372026-06-24evidence
Seed 2.1 TurboByteDance0.6292026-06-24evidence

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.