whatmodel.sh / image / Gemini 2.0 Flash Image Generation (preview)

Gemini 2.0 Flash Image Generation (preview)

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

Gemini 2.0 Flash Image Generation (preview) is a closed-weights image model from Google, released May 2025.

Model information sources

Release date ↗

44.9±1.8comparison only: no current run option verifiedfrom 5 benchmark results across 3 sources

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

$ how it compares

The image models ranked either side of Gemini 2.0 Flash Image Generation (preview), out of 197 with a score, then more from Google.

#modelscorewhereRAMreleased
120FLUX1.1 [pro] Black Forest Labs46±2api $0.040/image2024-10
121Midjourney V6 Midjourney45±7comparison only2023-12
122Gemini 2.0 Flash Image Generation (preview) Google45±2comparison only2025-05
123Show-o2 1.5B Show Lab, NUS45±5comparison only2025-06
124DeepGen 1.0 DeepGen Team45±3comparison only2026-02
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▁▂▇▇▆▅█▇▂▃▁▁ #90 of 157 · 77% of its score · 3 tests

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), FLUX1.1 [pro] here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LMArena text-to-image975.3 ✎▂▃▃▄▇█▄▂▄▂·▂ beats 5/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%typical
GenEval66.9% ✎██·▄·▄·█···▄ beats 4/8easy · avg 71%▇▇▇▇▇▇▇ 18%at its level
MMMG image generation (average over 15 tasks)59.2% ✎█··█▄▄·▄▄·▄▄ beats 7/9medium · avg 51%▇▇▇▇ 8.9%at its level
image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #73 of 81 * · 22% of its score · 2 tests

Trails Stable Diffusion 3.5 Large, OmniGen2, BAGEL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image edit1080.8 ✎▂▃▁▂▆▇█▄▆▅▁▂ beats 2/53avg 1153▇▇▇▇▇▇▇▇ 19%typical
OmniContext average (GPT-4.1 judge)36.2% ✎▃▃▃··▃·····█ beats 0/6medium · avg 65%▇ 3.0%at its level · noisy

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 69%, MMMG: a Comprehensive and Rel… 27%, BAAI — OmniGen2 technical rep… 3%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 69%CC BY 4.0
MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)2▇▇▇▇▇▇▇▇ 27%CC-BY-4.0
BAAI — OmniGen2 technical report1▇ 3%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 44.9

$ 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