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

Reward Alignment on RBM-EVAL OOD

0.96Pearson r (VOC)

ACE-Brain-0.5

Updated 18d ago

Evaluation Results

Method	Links
ACE-Brain-0.5 2026.07		0.96
ROBOMETER 2026.03		0.95
Robometer-4B 2026.07		0.94
ROBOMETER 2026.03		0.93
RoboReward-4B 2026.03		0.88
RoboReward-8B 2026.03		0.88
RoboReward-8B 2026.07		0.88
Qwen3-VL-8B 2026.07		0.87
RoboDopamine-8B 2026.07		0.8
ReWiND 2026.03		0.51
GVL 2026.03		0.21
VLAC 2026.03		0.17
VLAC-8B 2026.07		0.17
RoboDopamine 2026.03		0.08