Reward Model Evaluation on internally annotated (test) benchmark leaderboard · SOTA2 Research

Reward Model Evaluation on internally annotated (test)

0.762PLCCGDSO

Evaluation Results

Method	Links
GDSO2026.06		0.762	0.7132	89.56	98.85
RISD2026.06		0.7391	0.6882	88.64	98.01
GRPO2026.06		0.72	0.6832	86.04	98.27
RewardDance2026.06		0.6667	0.6207	84.25	97.06
SFT2026.06		0.6458	0.5914	81.35	96.44
GDSO2026.06		0.6341	0.5665	83.95	95.99
Zero-shot2026.06		0.6301	0.5816	74.38	95.38
GRPO2026.06		0.534	0.5072	77.03	90.76
SFT2026.06		0.5296	0.4942	74.59	84.01
RewardDance2026.06		0.5182	0.4338	78.17	89.72
Zero-shot2026.06		0.3411	0.3167	65.63	75.01