whatmodel.sh / image / MAI-Image-2
MAI-Image-2
↗ share
+ contribute
MAI-Image-2 is a closed-weights image model from Microsoft AI, released March 2026.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of MAI-Image-2, out of 197 with a score, then more from Microsoft AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 23 |  Ideogram 4.0 | 66±2 | api $0.060/image +local | ||
| 24 |  Qwen-Image 2.0 Pro | 66±3 | api $0.075/image | ||
| 25 | MAI-Image-2 | 66±3 | comparison only | ||
| 26 |  Grok Imagine Image | 66±2 | api $0.020/image | ||
| 27 |  Uni-1.1 Max | 65±2 | api $0.10/image | ||
| more from Microsoft AI | |||||
| 4 | MAI-Image-2.6 | 81±2 | comparison only | ||
| 15 | MAI-Image-2.5 | 74±2 | comparison only | ||
| 71 | MAI-Image-1 | 57±3 | comparison only | ||
$ what it's good at
text to image▁▂▇▇▆▅█▇▂▃▁▁ #24 of 157 * · 97% of its score · 1 test
Trails Uni-1.1 Max here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1183.8 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 54/75 | 97% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 97%
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 | 97% |
| prior · pull toward the middle | 3% | |
| weighted average | = 66.0 |
$ 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