whatmodel.sh / image / MAI-Image-2.5

MAI-Image-2.5

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

MAI-Image-2.5 is a closed-weights image model from Microsoft AI, released June 2026. Licence: proprietary.

Catalogue identity notes

Comparison-only. Arena text_to_image entry 'mai-image-2.5' (microsoft-ai, Proprietary), first listed 2026-06-03. Predecessor of catalogued mai-image-2-6.

Model information sources

Release date ↗

74.0±2.1comparison only: no current run option verifiedfrom 3 benchmark results across 2 sources

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of MAI-Image-2.5, out of 197 with a score, then more from Microsoft AI.

#modelscorewhereRAMreleased
13Reve 2.0 Reve74±2api $0.25/image2026-06
14ChatGPT Image Latest (chatgpt-image-latest) OpenAI74±4api $0.034/image2025-12
15MAI-Image-2.5 Microsoft AI74±2comparison only2026-06
16Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) Google73±2api $0.034/image2026-06
17GPT Image 1.5 OpenAI71±1api $0.034/image2025-12
more from Microsoft AI
4MAI-Image-2.6 Microsoft AI81±2comparison only2026-08
25MAI-Image-2 Microsoft AI66±3comparison only2026-03
71MAI-Image-1 Microsoft AI57±3comparison only2025-11

see all image models · find the ones that fit your machine

$ what it's good at

text to image▁▂▇▇▆▅█▇▂▃▁▁ #14 of 157 * · 64% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1254.2 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 63/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%typical
image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #8 of 81 * · 24% of its score · 1 test

Beats Reve 2.1, Nano Banana 2 (Gemini 3.1 Flash Image), Nano Banana Pro (Gemini 3 Pro Image) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
Arena image edit1400.9 ✎▂▁▁▂▆▇█▄▆▅▁▂ beats 46/53avg 1153▇▇▇▇▇▇▇▇▇▇ 24%typical
other tests1 not in a task · 10% of its score
testresultvs the others in its rundifficultycountswhy
Rapidata Benchmark.ai image benchmark (overall Elo)1042.1 ✎▁▁▁▄▂█▃▁▁▂▁▁ beats 24/34avg 875▇▇▇▇ 10%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 88%, Rapidata/text-to-image-human-… 10%

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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%CC BY 4.0
Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings1▇▇▇ 10%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 74.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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