whatmodel.sh / video / Seedance 1.5 Pro
Seedance 1.5 Pro
↗ share
+ contribute
Seedance 1.5 Pro is a closed-weights video model from ByteDance Seed, released December 2025. Licence: proprietary.
$ how it compares
The video models ranked either side of Seedance 1.5 Pro, out of 139 with a score, then more from ByteDance Seed.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 37 |  Wan 2.1 I2V Plus | 58±5 | api price unknown | ||
| 38 |  Cosmos3-Super | 58±4 | local | ||
| 39 | Seedance 1.5 Pro | 58±2 | api $0.052/sec | ||
| 40 |  Kling 2.5 Turbo Pro | 57±2 | api $0.070/sec | ||
| 41 |  Runway Aleph | 56±5 | comparison only | ||
| more from ByteDance Seed | |||||
| 5 | Dreamina Seedance 2.0 | 79±1 | api $0.30/sec | ||
| 43 | Seedance 1.0 Pro | 56±2 | api $0.052/sec | ||
| 65 | Seaweed-7B | 50±6 | comparison only | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #16 of 68 * · 45% of its score · 2 tests
Beats Wan 2.5 Preview, Kling 2.6 Pro, PixVerse V5.6 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1256.0 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 23/41 | 39% |
| Cosmos HUE human evaluation, text-to-video (Cosmos 3 report) | 90.0% ✎ | █▄▄··▄▄▄▄▄·▄ beats 8/9 | 6.0% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #37 of 50 · 47% of its score · 4 tests
Trails Cosmos3-Nano, Kling 2.1 Master, Hailuo 02 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1307.2 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 20/40 | 26% |
| Rapidata physics realism (I2V, with reference) | 697.0 ✎ | ▃··▂▂▆█▆▂▂▆▄ beats 0/19 | 15% |
| Cosmos HUE human evaluation, image-to-video (Cosmos 3 report) | 87.6% ✎ | ▄·█··▄··▄▄▄█ beats 4/8 | 4.9% |
| What-If World causal-intervention video generation (APEO paired average, Gemini 3.1 Pro judge) | 32.4% ✎ | █·▄····▄···█ beats 2/5 | 2.1% |
other tests1 not in a task · 6.5% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MindWorldBench intention accuracy (I2V mental-state reasoning) | 29.3% ✎ | ▅·▃▅·█·▃···▃ beats 7/9 | 6.5% |
$ where to run it
Through an API
api · fal.ai · $0.052/sec · fal.ai ↗ · price sourceUSD per second, 720p with audio, derived from fal's own figure that a 720p 5-second video with audio costs roughly $0.26 (÷ 5); provider-published approximation. Product: fal Seedance 1.5 Pro text-to-video endpoint. API model: fal-ai/bytedance/seedance/v1.5/pro/text-to-video. Underlying billing is per video token ($2.4/1M with audio, $1.2/1M without); no per-second figure is printed for other settings, so none is derived. Not the BytePlus direct tariff. Currency: USD. fal.ai model page, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 65%, Rapidata/world-model-physics… 15%, Cosmos 3: Omnimodal World Mod… 11% and 2 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 | 2 | 65% |
 Rapidata/world-model-physics published dataset-card rankings | 1 | 15% |
 Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4) | 2 | 11% |
| MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1) | 1 | 7% |
| What-If World: A Causal Benchmark for General World Models in Embodied Scenarios (arXiv:2605.27589v1), Table 2 | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 57.5 |
$ 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