whatmodel.sh / image / Imagen 3 (imagen-3.0-generate-002)

Imagen 3 (imagen-3.0-generate-002)

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

Imagen 3 (imagen-3.0-generate-002) is a closed-weights image model from Google, released January 2025.

Model information sources

Release date ↗

51.6±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 Imagen 3 (imagen-3.0-generate-002), out of 197 with a score, then more from Google.

#modelscorewhereRAMreleased
94Ideogram 3.0 Ideogram52±2api $0.060/image2025-03
95UniPic 3 Skywork AI52±3comparison only2026-01
96Imagen 3 (imagen-3.0-generate-002) Google52±2comparison only2025-01
97FLUX.2 [klein] 4B Black Forest Labs52±2api $0.0011/image +local~2.9GB2026-01
98P-Image Pruna51±2api $0.0050/image2025-12
more from Google
5Nano Banana 2.1 Google81±2api $0.034/image2026-10
9Nano Banana 2 (Gemini 3.1 Flash Image) Google76±1api $0.067/image2026-02
10Nano Banana Pro (Gemini 3 Pro Image) Google76±1api $0.13/image2025-11

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

$ what it's good at

text to image▁▂▇▇▆▅█▇▂▃▁▁ #75 of 157 · 98% of its score · 3 tests

Trails FLUX.1 Kontext [pro] here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1058.0 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 17/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%typical
GenEval70.7% ✎██·▄·▄·█···▄ beats 5/8easy · avg 71%▇▇▇▇▇▇▇▇ 20%at its level
MMMG image generation (average over 15 tasks)47.4% ✎█··█▄▄·▄▄·▄▄ beats 4/9medium · avg 51%▇▇▇▇▇ 12%at its level

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 66%, MMMG: a Comprehensive and Rel… 32%

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 dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%CC BY 4.0
MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)2▇▇▇▇▇▇▇▇▇▇ 32%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 51.6

$ 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