Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VideoScore2: Think before You Score in Generative Video Evaluation

About

Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic alignment, and physical consistency. Existing evaluators and reward models are limited to single opaque scores, lack interpretability, or provide only coarse analysis, making them insufficient for capturing the comprehensive nature of video quality assessment. We present VideoScore2, a multi-dimensional, interpretable, and human-aligned framework that explicitly evaluates visual quality, text-to-video alignment, and physical/common-sense consistency while producing detailed chain-of-thought rationales. Our model is trained on a large-scale dataset VideoFeedback2 containing 27,168 human-annotated videos with both scores and reasoning traces across three dimensions, using a two-stage pipeline of supervised fine-tuning followed by reinforcement learning with Group Relative Policy Optimization (GRPO) to enhance analytical robustness. Extensive experiments demonstrate that VideoScore2 achieves superior performance with 44.35 (+5.94) accuracy on our in-domain benchmark VideoScore-Bench-v2 and 50.37 (+4.32) average performance across four out-of-domain benchmarks (VideoGenReward-Bench, VideoPhy2, etc), while providing interpretable assessments that bridge the gap between evaluation and controllable generation through effective reward modeling for Best-of-N sampling. Project Page: https://tiger-ai-lab.github.io/VideoScore2/

Xuan He, Dongfu Jiang, Ping Nie, Minghao Liu, Zhengxuan Jiang, Mingyi Su, Wentao Ma, Junru Lin, Chun Ye, Yi Lu, Keming Wu, Benjamin Schneider, Quy Duc Do, Zhuofeng Li, Yiming Jia, Yuxuan Zhang, Guo Cheng, Haozhe Wang, Wangchunshu Zhou, Qunshu Lin, Yuanxing Zhang, Ge Zhang, Wenhao Huang, Wenhu Chen• 2025

Related benchmarks

TaskDatasetResultRank
Content Quality AssessmentUltraVQA
Acc@0.560.2
14
Motion Quality AssessmentUltraVQA
Acc@0.569.8
14
Aesthetic Quality AssessmentUltraVQA
Accuracy @0.563.7
14
Clarity Quality AssessmentUltraVQA
Acc@0.575.3
14
Motion Amplitude AssessmentUltraVQA
Accuracy@0.570.5
14
Human Preference AlignmentREACT-Video
Acc (Tie, Overall)34.2
12
Video Preference AlignmentGenAI-Bench
Alignment Accuracy (w/ties)39.1
11
Physical ReasoningVideoPhy 2
Accuracy0.386
8
Video Preference AssessmentMJ-Video
Acc65.8
8
Video Generation AssessmentGenAI-Bench Video (test)
Accuracy70.6
8
Showing 10 of 12 rows

Other info

Follow for update