Skip to content
Bencher

TestsBenchmarks · Multimodal

BabyVision

Basic visual reasoning.

% solvedHigher is betterThe test's websiteOfficial page ↗

The best 2 · 2 models tested

Top 2 · best setting per model · 2 models, 2 results (0 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported
BabyVision leaderboard
Thinking levelSetting
1Muse Spark 1.1Meta (Meta Superintelligence Labs, Muse)76.3%Defaulteffort not statedMaker's own figureVendor-reportedMeta ↗—9 Jul 2026
2Muse SparkMeta (Meta Superintelligence Labs, Muse)39.9%Defaulteffort not statedMaker's own figureVendor-reportedMeta ↗—9 Jul 2026