List your company

Reward Modeling on Unified Feedback (UF)

78.9AccuracyGRM-SFT
68.08470.89273.776.508Feb 11, 2026

Evaluation results

MethodLinks
GRM-SFTBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0278.9
BT-BNRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0278.8
GRM-BNRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0278.7
BT-MarginBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0277.3
GRM-DPOBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0277.3
InfoRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0277.3
BT-BNRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0277.2
BT-BNRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0277
GRM-BNRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0276.9
BT-EnsembleBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0276.9
GRM-DPO-NorefBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0276.7
GRM-BNRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0276.6
BTBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0276.6
BT-LabelSmoothBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 400K2026.0276.6
InfoRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0276.2
GRM-SFTBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0275.8
GRM-DPOBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0275.5
GRM-DPO-NorefBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0275.2
BT-EnsembleBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0275.1
BT-MarginBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0274.7
BT-LabelSmoothBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0274.7
BTBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0274.5
BT-BNRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0274.2
GRM-BNRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0274.1
InfoRMBackbone=Gemma2 2B it, Training Scale=Unified-Feedback 40K2026.0273.9
GRM-DPO-NorefBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0273.9
GRM-DPOBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0273.8
GRM-SFTBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0273.2
BT-EnsembleBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0272.8
BTBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0272.1
BT-MarginBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0272
InfoRMBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0271.6
GRM-SFTBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0271.5
BT-LabelSmoothBackbone=Gemma 2B it, Training Scale=Unified-Feedback 400K2026.0271.5
GRM-DPO-NorefBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0271.4
GRM-DPOBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0270.2
BT-EnsembleBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0269.9
BT-MarginBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0269.6
BTBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0268.8
BT-LabelSmoothBackbone=Gemma 2B it, Training Scale=Unified-Feedback 40K2026.0268.5