whatmodel.sh / image / SeedEdit 3.0
SeedEdit 3.0
↗ share
+ contribute
SeedEdit 3.0 is a closed-weights image model from ByteDance Seed, released June 2025.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of SeedEdit 3.0, out of 197 with a score, then more from ByteDance Seed.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 110 |  VQ-Diffusion (ITHQ) | 48±15 | local | ||
| 111 | LAFITE (HPS v2 checkpoint) | 48±15 | comparison only | ||
| 112 | SeedEdit 3.0 | 48±3 | comparison only | ||
| 113 |  Ovis-Image-7B | 48±7 | local | ||
| 114 |  FLUX.1 Krea [dev] | 47±3 | api $0.025/image +local | ||
| 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▁▂▇▇▆▅█▇▂▃▁▁ #118 of 157 * · 30% of its score · 1 test
Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ) here, though they rank higher overall. Trails SDXL-Lightning (4-step UNet), Stable Cascade, BLIP3-o 8B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ServImage task acceptance (human payment decisions, commercial design tasks) | 7.0% ✎ | ▃▃··▂··▃█··▂ beats 0/11 | 30% |
image to image / editing▁▁▁▃▃▃█▃▃▃▁▁ #63 of 81 · 97% of its score · 3 tests
Beats FLUX.1 Kontext [pro] here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1138.9 ✎ | ▂▁▁▃▆▇█▄▆▅▁▂ beats 5/53 | 44% |
| ServImage task acceptance (human payment decisions, commercial design tasks) | 7.0% ✎ | ▃▃··▂··▃█··▂ beats 0/11 | 30% |
| UnicBench (EN, overall) | 78.7% ✎ | ▂····▂▄▂▄·█▂ beats 8/11 | 23% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 44%, ServImage: An Image Generatio… 30%, UnicEdit-10M: A Dataset and B… 23%
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 | 44% |
 ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2) | 1 | 30% |
| UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits | 1 | 23% |
| prior · pull toward the middle | 3% | |
| weighted average | = 47.5 |
$ 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