Decision support
Veo 3 vs Kling 2.1 Master
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Google DeepMind
Kling
Benchmark results
Head to head on 2 benchmarks both models report
- Veo 32leads
- Kling 2.1 Master0leads
Arena Text to Video
Arena rating · Higher is better
- Veo 3Best1254+91 ahead · Arena #25CI 1243 to 1265
- Kling 2.1 Master1163Arena #42CI 1153 to 1173
Runs and sources
Veo 3- default125495% CI 1243 to 1265 · 15,017 votes
Kling 2.1 Master- default116395% CI 1153 to 1173 · 14,104 votes
Arena Image to Video
Arena rating · Higher is better
- Veo 3Best1259+23 ahead · Arena #32CI 1249 to 1270
- Kling 2.1 Master1236Arena #36CI 1228 to 1244
Runs and sources
Veo 3- default125995% CI 1249 to 1270 · 26,105 votes
Kling 2.1 Master- default123695% CI 1228 to 1244 · 29,824 votes
Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.
Model specifications
API pricing · USD per 1M tokens
Capabilities and modalities
Architecture and availability
A dash means the field is not reported. Provider-specific performance and pricing may differ.