whatmodel.sh / video / Dreamina Seedance 2.5
Dreamina Seedance 2.5
↗ share
+ contribute
Dreamina Seedance 2.5 is a closed-weights video model from ByteDance, released July 2026.
Model information sources
$ how it compares
The video models ranked either side of Dreamina Seedance 2.5, out of 139 with a score, then more from ByteDance.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 5 |  Dreamina Seedance 2.0 | 79±1 | api $0.30/sec | ||
| 6 |  MiniMax H3 | 78±1 | api $0.13/sec +local | ||
| 7 | Dreamina Seedance 2.5 | 77±1 | api $0.30/sec | ||
| 8 |  FLUX 3 Video | 77±2 | api $0.17/sec | ||
| 9 |  HappyHorse 1.1 | 76±3 | api $0.14/sec | ||
| more from ByteDance | |||||
| 32 | Seedance 1.0 Pro Fast | 62±11 | api $0.049/sec | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #6 of 68 * · 36% of its score · 1 test
Beats MiniMax H3 here, though they rank higher overall. Trails FLUX 3 Video here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1473.9 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 36/41 | 36% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #5 of 50 * · 37% of its score · 2 tests
Beats Wan 3.0 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1477.4 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 37/40 | 24% |
| Rapidata physics realism (I2V, with reference) | 1247.0 ✎ | ▂··▂▂▆█▆▂▃▆▄ beats 14/19 | 14% |
video editing▄··█··▄··█▄█ #2 of 9 * · 7.3% of its score · 1 test
Beats Gemini Omni Flash, Dreamina Seedance 2.0, MiniMax H3 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena video edit | 1409.8 ✎ | █··█··▄··█▄█ beats 8/9 | 7.3% |
other tests4 not in a task · 19% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata relative camera movement (I2V, alignment Elo) | 1076.3 ✎ | █···▄▄██·█▄█ beats 5/12 | 8.4% |
| Rapidata image-to-video realism (overall Elo) | 1175.6 ✎ | ▂······▃▂▃▃█ beats 4/12 | 4.5% |
| WROP object-permanence exam (human Elo) | 1649.6 ✎ | ▄····██···▄█ beats 5/7 | 3.8% |
| Datapoint Video Bench (overall Elo) | 1049.3 ✎ | ▃▃·▅·▃·▃··▃█ beats 9/9 | 2.0% |
$ where to run it
Through an API
api · Runway · $0.30/sec · docs.dev.runwayml.com ↗ · price sourceUSD per second of output video, 720p, on the Runway developer API. Product: Runway API video generation. API model: seedance2_5 (Seedance 2.5). Settings: resolution=720p, no input/reference video. Price basis: 30 credits per output second × $0.01 per credit. Input and reference video add 15 credits/s; 80-credit minimum per generation; 480p 20 credits/s, 1080p 68 credits/s. BytePlus bills Seedance per token and prints no exact per-second rate; fal lists roughly $0.4730/s at 720p. Sales tax excluded. Currency: USD. Runway API pricing documentation, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 67%, Rapidata/world-model-physics… 14%, Rapidata/relative-camera-move… 8% and 3 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 3 | 67% |
 Rapidata/world-model-physics published dataset-card rankings | 1 | 14% |
| Rapidata/relative-camera-movement-human-preference-900k published dataset-card rankings | 1 | 8% |
| Rapidata/image-to-video-realism published dataset-card rankings | 1 | 5% |
 Training Object Permanence in World Models (WROP exam; arXiv:2609.28654v1) | 1 | 4% |
| Datapoint Video Bench leaderboard (datapointai/text-to-video-human-preferences-326k dataset card) | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 77.4 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json