Codesota · Benchmark · VBenchHome/Leaderboards/Multimodal Media/Text-to-Video/VBench
Unknown

VBench.

Comprehensive text-to-video generation benchmark across 16 dimensions

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Only 4 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Total Score

Total Score is the reported evaluation metric for VBench. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Total Scoreverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01Kling 1.0
Kling 1.0 (Kuaishou). VBench total score (%). Official VBench leaderboard.
verified85.372024Source ↗Looks wrong?
02Runway Gen-3 Alpha
Runway Gen-3 Alpha. VBench total score (%). Official VBench leaderboard. Evaluated 2024.
verified85.222024Source ↗Looks wrong?
03CogVideoX-5B
CogVideoX-5B (Zhipu AI). VBench total score (%). Reported in paper Table 2 and VBench leaderboard.
verified82.752024Source ↗Looks wrong?
04Open-Sora 1.2
Open-Sora 1.2 (HPC-AI Tech). VBench total score (%). Official VBench leaderboard.
verified80.912024Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Text-to-Video