whatmodel.sh / image / Seedream 3.0
Seedream 3.0
↗ share
+ contribute
Seedream 3.0 is a closed-weights image model from ByteDance Seed, released April 2025.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Seedream 3.0, out of 197 with a score, then more from ByteDance Seed.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 71 |  MAI-Image-1 | 57±3 | comparison only | ||
| 72 |  LongCat-Image-Edit | 56±2 | api $0.15/image +local | ||
| 73 | Seedream 3.0 | 56±2 | comparison only | ||
| 74 |  P-Image-Edit | 56±4 | api $0.010/image | ||
| 75 |  FireRed-Image-Edit-1.0 | 56±4 | comparison only | ||
| more from ByteDance Seed | |||||
| 12 | Seedream 5.0 Pro | 75±2 | api $0.050/image | ||
| 29 | Seedream 5.0 Lite | 65±2 | api $0.035/image | ||
| 45 | Seedream 4.0 | 61±1 | api $0.040/image | ||
$ what it's good at
text to image▁▂▇▇▆▅█▇▂▃▁▁ #64 of 157 · 86% of its score · 3 tests
Beats HunyuanImage 2.1 here, though they rank higher overall. Trails LLaDA-Image, Z-Image-Turbo, Qwen-Image-2512 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1081.6 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 21/75 | 49% |
| ServImage task acceptance (human payment decisions, commercial design tasks) | 31.4% ✎ | ▂▃··▂··▃█··▂ beats 9/11 | 19% |
| GenExam (relaxed overall, GPT-5 judge) | 23.4% ✎ | ▆▆·▂▂····▂▂█ beats 3/13 | 18% |
image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #44 of 81 * · 19% of its score · 1 test
Beats Imagen 4, GPT Image 1 Mini, FLUX.2 [dev] here, though they rank higher overall. Trails FLUX.2 [klein] 9B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ServImage task acceptance (human payment decisions, commercial design tasks) | 31.4% ✎ | ▂▃··▂··▃█··▂ beats 9/11 | 19% |
other tests1 not in a task · 13% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata human-face generation alignment (Elo) | 1123.6 ✎ | ▃··▅▃··▃▃··█ beats 8/8 | 13% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 49%, ServImage: An Image Generatio… 19%, GenExam leaderboard (OpenGVLa… 18% and 1 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 | 1 | 49% |
 ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2) | 1 | 19% |
 GenExam leaderboard (OpenGVLab/GenExam README, relaxed score) | 1 | 18% |
 Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard | 1 | 13% |
| prior · pull toward the middle | 1% | |
| weighted average | = 56.0 |
$ 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