List your company

Scientific Review Evaluation on Scientific Review Human Evaluation Dataset

66.7Actionability Win RateProReviewer
50.68454.8425963.158Jun 11, 2026

Evaluation results

MethodLinks
ProReviewerMethod Model=Qwen3-8B, Opponent=AI-Sci-v2, Opponent Model Scale=397B2026.0666.714.385.7057.19.576.29.5
ProReviewerMethod Model=Qwen3-8B, Opponent=CycleReviewer, Opponent Model Scale=8B2026.0661.57.794.9082.1082.12.6
ProReviewerMethod Model=Qwen3-8B, Opponent=AgentReview, Opponent Model Scale=397B2026.0657.114.376.29.561.914.371.49.5
ProReviewerMethod Model=Qwen3-8B, Opponent=DeepReview, Opponent Model Scale=8B2026.0651.323.174.47.761.515.469.217.9