List your company

Preference Prediction on RewardBench

92.2AccuracySkywork-Critic-Llama3.1-70B
66.272.9579.786.45Apr 15, 2026Apr 23, 2026May 1, 2026May 9, 2026May 17, 2026May 25, 2026Jun 2, 2026

Evaluation results

MethodLinks
Skywork-Critic-Llama3.1-70B2026.0692.2
C2Backbone=Qwen3-8B2026.0491.8
Reasoning RM + External-Rubric (32B)Backbone=Qwen3-8B2026.0491.3
Reasoning RM + Self-RubricBackbone=Qwen3-8B2026.0490.8
SenseJudge2026.0690.55
Reasoning RMBackbone=Qwen3-8B2026.0489.8
Base ModelBackbone=Qwen3-8B2026.0489.1
Gemini-1.5-pro-05142026.0688.2
Reasoning RM + External-Rubric (32B)Backbone=Tulu3-8B-SFT2026.0484.9
Gpt-4o-2024-05-132026.0684.6
Meta-Llama-3.1-70B-Instruct2026.0684
Claude-3-opus-202402292026.0680.1
C2Backbone=Tulu3-8B-SFT2026.0477.2
EvoPrefOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0575.5
ORPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0575
DPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574.9
SMS-EMOAOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574.8
EvoPref-BestOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574.8
MOEA/DOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574.5
KTOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574.1
CMA-ESOptimization Paradigm=Single-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0574
IPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0573.8
Reasoning RMBackbone=Tulu3-8B-SFT2026.0473.7
Reasoning RM + Self-RubricBackbone=Tulu3-8B-SFT2026.0470.8
Base ModelBackbone=Tulu3-8B-SFT2026.0467.2