Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spatial Reasoning on SQuID Tier 2

54.06Accuracy

QVLM

33.291238.683144.07549.4669Jan 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
54.06
2026.01
47.62
2026.01
41.88
2026.01
40.22
2026.01
36.85
2026.01
34.09