Decision support
Wan 2.5 Preview vs Sora 2
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Alibaba
OpenAI
Benchmark results
Head to head on 1 benchmark both models report
- Wan 2.5 Preview0leads
- Sora 21lead
Arena Text to Video
Arena rating · Higher is better
- Wan 2.5 Preview1244Arena #27CI 1236 to 1253
- Sora 2Best1342+98 ahead · Arena #19CI 1336 to 1348
Runs and sources
Wan 2.5 Preview- default124495% CI 1236 to 1253 · 43,113 votes
Sora 2- default134295% CI 1336 to 1348 · 73,992 votes
Arena Image to Video
Arena rating · Higher is better
- Wan 2.5 Preview1322Arena #24CI 1312 to 1332
- Sora 2Not reported
Runs and sources
Wan 2.5 Preview- default132295% CI 1312 to 1332 · 17,048 votes
Sora 2Not reported
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.