Get started

Graphic design · Models

Design Arena's Elo for graphic design · models, from pairwise human preference votes, as OpenRouter carries it. 5 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fwww.designarena.ai ↗

Most capable1261Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google
Best value1373Nano Banana (Gemini 2.5 Flash Image)1167 at $0.85 blended per M
Newest ranked1261Nano Banana 2 (Gemini 3.1 Flash Image Preview)listed 26 Feb 2026

2 models sit on the frontier: nothing scores higher for less.

  • the frontier
  • a priced model, in its maker's tone
  • on the frontier, named
$1.00$10.00116512131261Blended list price per M tokens, log scaleEloNano Banana 2 (Gemini 3.1 Flash Image Preview): 1261 · $1.125 blended · Google$1.125126102 Nano Banana 2 (Gemini 3.1 Flash Image Preview)1261 · $1.125 blended · GoogleNano Banana Pro (Gemini 3 Pro Image Preview): 1251 · $4.50 blended · Google$4.501251Nano Banana Pro (Gemini 3 Pro Image Preview)1251 · $4.50 blended · GoogleGPT-5 Image: 1172 · $10.00 blended · OpenAI$10.001172GPT-5 Image1172 · $10.00 blended · OpenAINano Banana (Gemini 2.5 Flash Image): 1167 · $0.85 blended · Google$0.85116701 Nano Banana (Gemini 2.5 Flash Image)1167 · $0.85 blended · GoogleGPT-5 Image Mini: 1165 · $2.375 blended · OpenAI$2.3751165GPT-5 Image Mini1165 · $2.375 blended · OpenAI
  1. 01Nano Banana (Gemini 2.5 Flash Image)1167 · $0.85 blended
  2. 02Nano Banana 2 (Gemini 3.1 Flash Image Preview)1261 · $1.125 blended · +94 at 1.3x

5 of 5 ranked models carry a list price; 0 are free or unlisted and not in the field. Price is the blended OpenRouter rate, three input tokens to one output, on a logarithmic axis. Each dot is filled in its maker's tone, as the columns above are. The numbered and named dots are the frontier, cheapest first; each step after the first names what it adds over the step before, and at what multiple of the blended price. A hover over any dot names it and its two figures, a click opens the model, and a model named in the picker above keeps its label on. 5 of the 5 crosses match the selection below and are drawn white.

5 of 5.

Design Arena · Elo
PositionModelAuthorEloWin rateSource rankIn / out per MContextListed
01Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google126166.3%4$0.50 / $3.0066k
02Nano Banana Pro (Gemini 3 Pro Image Preview)Google125165.8%5$2.00 / $12.0066k
03GPT-5 ImageOpenAI117248.9%9$10.00 / $10.00400k
04Nano Banana (Gemini 2.5 Flash Image)Google116756.9%10$0.30 / $2.5033k
05GPT-5 Image MiniOpenAI116547.7%11$2.50 / $2.00400k

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 5 of 5 models would say nothing beats them on both while something in the same board does. The models this table holds are drawn white in the figures instead.

What the score tells you

An Elo from pairwise human preference votes: a higher figure means the model's output was preferred more often against the field it was matched with. Win rate is the share of matchups won. Both shift as new models enter the arena, neither is a measure of correctness, and the source's own rank counts models this catalog does not carry.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.