whatmodel.sh / image / GPT Image 1 Mini
GPT Image 1 Mini
↗ share
+ contribute
GPT Image 1 Mini is a closed-weights image model from OpenAI, released October 2025. Licence: proprietary.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of GPT Image 1 Mini, out of 197 with a score, then more from OpenAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 55 |  FireRed-Image-Edit-1.1 | 59±4 | comparison only | ||
| 56 |  Krea 2 Turbo | 59±3 | api $0.015/image +local | ||
| 57 | GPT Image 1 Mini | 59±2 | api $0.011/image | ||
| 58 | Krea 2 Large | 59±3 | api $0.060/image | ||
| 59 |  Qwen-Image-Edit-2509 | 59±3 | api $0.030/image +local | ||
| more from OpenAI | |||||
| 1 | GPT Image 2.5 Sunburst | 92±2 | api $0.013/image | ||
| 2 | GPT Image 2.5 Flare | 88±2 | api $0.013/image | ||
| 3 | GPT Image 2 | 85±1 | api $0.053/image | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #45 of 126 * · 48% of its score · 2 tests
Beats Wan 2.7 Image, Krea 2 Turbo here, though they rank higher overall. Trails FLUX.2 [dev] here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1109.8 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 27/75 | 34% |
| ServImage task acceptance (human payment decisions, commercial design tasks) | 32.4% ✎ | ▂▃··▂··▃█··▂ beats 10/11 | 15% |
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #49 of 62 * · 27% of its score · 2 tests
Trails GLM-Image, FLUX.2 [klein] 4B, Ideogram 3.0 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ServImage task acceptance (human payment decisions, commercial design tasks) | 32.4% ✎ | ▂▃··▂··▃█··▂ beats 10/11 | 15% |
| Arena image edit | 1124.2 ✎ | ▂▁▃▂▆▇█▄▆▅▁▂ beats 3/53 | 13% |
other tests2 not in a task · 38% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VVRBench accuracy (10,000 verifiable synthetic-scene tasks) | 26.4% ✎ | ▃·█▅▃·▅▃···▃ beats 9/10 | 35% |
| VVRBench-Challenge accuracy (720 harder verifiable tasks) | 0.3% ✎ | ▄·▄···█·▄▄·▄ beats 0/6 | 2.3% |
$ where to run it
Through an API
api · $0.011/image · developers.openai.com ↗ · price sourceUSD for one generated 1024×1024 medium-quality image. Output-only published price; input text/image token charges are additional. Scheduled deprecation 2026-12-01. Product: Image generation API. API model: gpt-image-1-mini. Settings: quality=medium, width=1024, height=1024, n=1. Price basis: generated image output component. Additional/excluded charges: input text/image tokens. Currency: USD.
$ how the score was worked out · LMArena leaderboard dataset 47%, Verifiable Visual Rewards Tra… 38%, ServImage: An Image Generatio… 15%
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 | 47% |
 Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1 | 2 | 38% |
| ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2) | 1 | 15% |
| prior · pull toward the middle | 1% | |
| weighted average | = 58.6 |
$ 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