whatmodel.sh / image / Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image)

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

Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is a closed-weights image model from Google, released June 2026. Licence: proprietary.

Catalogue identity notes

Comparison-only. Arena text_to_image entry 'gemini-3.1-flash-lite-image (nano-banana-2-lite)' (google, Proprietary), first listed 2026-06-30. Distinct from nano-banana-2.

Model information sources

Release date ↗

73.0±2.0#14 of 144 image modelsfrom 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 Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image), out of 197 with a score, then more from Google.

#modelscorewhereRAMreleased
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
18Qwen-Image-2.1 Alibaba69±2local~12GB2026-09
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▂▅▅▃▄▄█▃▃▂▁▁ #13 of 126 * · 61% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1250.2 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 62/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 61%typical
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #19 of 62 * · 23% of its score · 1 test

Trails Grok Imagine Image Pro, Uni-1.1 Max, Grok Imagine Image here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image edit1313.5 ✎▂▁▁▂▆▇█▄▆▅▁▂ beats 33/53avg 1153▇▇▇▇▇▇▇▇▇ 23%typical
other tests1 not in a task · 13% of its score
testresultvs the others in its rundifficultycountswhy
VVRBench-Challenge accuracy (720 harder verifiable tasks)7.4% ✎▄·▄···█·▄▄·▄ beats 4/6very hard · avg 0.6%▇▇▇▇▇ 13%sharp · too hard for it

$ where to run it

Through an API

api · $0.034/image · ai.google.dev ↗ · price sourceUSD per 1K (1024×1024) generated image on the Gemini Developer API Standard paid tier: image output is $30 per 1M tokens and Google states a 1K output image consumes 1,120 tokens, 'equivalent to $0.0336 per image' (Batch: $0.0168). Input tokens and text/thinking output ($0.25 and $1.50 per 1M) are additional. Product: Gemini Developer API. API model: gemini-3.1-flash-lite-image. Settings: tier=Standard paid, resolution=1K, batch=no, n=1. Price basis: provider-published per-image equivalent of the image-output rate. Currency: USD. Google Gemini API official pricing page, observed 2026-09-25.

$ how the score was worked out · LMArena leaderboard dataset 85%, Verifiable Visual Rewards Tra… 13%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%CC BY 4.0
Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v11▇▇▇▇ 13%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 73.0

$ 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