List your company
ResearchFormerly WizWand

Spatial Reasoning on Spatial Reasoning (out-of-distribution)

53.64AccuracyCalibRL
37.57241.743545.91550.0865Feb 22, 2026
Updated 8mo ago

Evaluation results

MethodLinks
CalibRL2026.0253.64
DAPO2026.0250.21
LUFFY2026.0248.18
GRPO2026.0248.02
RL-PLUS2026.0247.55
SFT+GRPO2026.0238.19