The creative model reference

AI models for graphic design

Compare image generators for graphic design and layout-oriented creative work.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

image / Graphic Design

The scores, in perspective.

7 models · 95% intervals

Swipe to compare all models →

Oakgen Arena · v1.0

11,051

GPT Image 2

21,000

Grok Imagine 2.0Anchor

3975

Seedream 5.0 Pro

4952

Nano Banana Pro

5952

Nano Banana 2

6936

Qwen Image 3.0

7901

Flux.2 Pro

↥ 95% confidence interval · Anchor interval not reported.7 ranked models

Relative scores on a zero-based display scale. Compare within this board only. Values are rounded for display.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

Published reference / v1.0

Graphic Design leaderboard

Graphic Design image rankings · Benchmark index 1.0
Rank	Model	Overall score	95% confidence interval	Vote appearances	Distinct judges
01	GPT Image 2OpenAI Criterion scores Creativity / variation1,081.995% CI 1,037.4 to 1,128.3Reused fit from master-image Layout1,084.995% CI 1,026.3 to 1,151.4 Prompt adherence1,041.595% CI 1,010.7 to 1,074.8Reused fit from master-image Reference adherence1,035.395% CI 987 to 1,083.2Reused fit from master-image Style adherence1,049.695% CI 996.9 to 1,109.6 Subjective aesthetics1,030.195% CI 987.2 to 1,071.2Reused fit from master-image Text accuracy1,12095% CI 1,033.1 to 1,233.2 Typography953.395% CI 872.9 to 1,032.4	1,050.5LEAD	1,025.6 to 1,078.1	2,678	Not reported
02	Grok Imagine 2.0xAI Criterion scores Creativity / variation1,00095% CI Anchor · interval not reportedReused fit from master-image Layout1,00095% CI Anchor · interval not reported Prompt adherence1,00095% CI Anchor · interval not reportedReused fit from master-image Reference adherence1,00095% CI Anchor · interval not reportedReused fit from master-image Style adherence1,00095% CI Anchor · interval not reported Subjective aesthetics1,00095% CI Anchor · interval not reportedReused fit from master-image Text accuracy1,00095% CI Anchor · interval not reported Typography1,00095% CI Anchor · interval not reported	1,000#2Anchor	Anchor · interval not reported	2,714	Not reported
03	Seedream 5.0 ProByteDance Criterion scores Creativity / variation1,102.695% CI 1,050.6 to 1,156.5Reused fit from master-image Layout943.495% CI 894.1 to 994.5 Prompt adherence1,022.295% CI 982.2 to 1,060.8Reused fit from master-image Reference adherence1,036.795% CI 988.2 to 1,080Reused fit from master-image Style adherence896.795% CI 824.9 to 957.2 Subjective aesthetics1,042.895% CI 990.5 to 1,095.7Reused fit from master-image Text accuracy1,044.195% CI 931.3 to 1,181 Typography883.595% CI 798.8 to 957.4	974.7#3	944.9 to 1,008.2	2,695	Not reported
04	Nano Banana ProGoogle Criterion scores Creativity / variation1,032.295% CI 978.2 to 1,084.8Reused fit from master-image Layout94795% CI 885.1 to 1,012.2 Prompt adherence1,018.395% CI 978.4 to 1,058.1Reused fit from master-image Reference adherence1,002.295% CI 948.1 to 1,052.2Reused fit from master-image Style adherence916.995% CI 849.9 to 986.2 Subjective aesthetics981.195% CI 930.5 to 1,027.6Reused fit from master-image Text accuracy965.695% CI 838.9 to 1,093.4 Typography884.595% CI 793.8 to 962.4	952.5	919.8 to 982.9	2,716	Not reported
05	Nano Banana 2Google Criterion scores Creativity / variation972.695% CI 913.5 to 1,028.8Reused fit from master-image Layout922.895% CI 869.3 to 979.3 Prompt adherence977.395% CI 937.4 to 1,017.6Reused fit from master-image Reference adherence990.895% CI 945.5 to 1,039.8Reused fit from master-image Style adherence953.995% CI 889.2 to 1,021.9 Subjective aesthetics1,000.495% CI 954 to 1,052.4Reused fit from master-image Text accuracy951.295% CI 859.1 to 1,044.5 Typography92395% CI 833.6 to 1,006.7	952	925.8 to 979	2,702	Not reported
06	Qwen Image 3.0Alibaba Criterion scores Creativity / variation997.195% CI 949.8 to 1,047.1Reused fit from master-image Layout95295% CI 879.4 to 1,023.8 Prompt adherence915.195% CI 880.5 to 949.6Reused fit from master-image Reference adherence973.295% CI 921.3 to 1,028.5Reused fit from master-image Style adherence951.695% CI 894 to 1,015.1 Subjective aesthetics979.495% CI 928.4 to 1,035.8Reused fit from master-image Text accuracy902.995% CI 816.6 to 999.6 Typography883.995% CI 797.6 to 969.2	935.7	906 to 963.9	2,692	Not reported
07	Flux.2 ProBlack Forest Labs Criterion scores Creativity / variation909.695% CI 857.1 to 961.2Reused fit from master-image Layout891.295% CI 820.7 to 960.4 Prompt adherence940.995% CI 907.8 to 976.6Reused fit from master-image Reference adherence881.195% CI 833.9 to 927.5Reused fit from master-image Style adherence918.695% CI 845.4 to 981 Subjective aesthetics977.795% CI 921.3 to 1,028.8Reused fit from master-image Text accuracy914.495% CI 831.9 to 996.6 Typography834.495% CI 753.9 to 910.9	900.9	872.4 to 926.7	2,703	Not reported

Ranks are the source’s published positions. Vote appearances are not unique people and must not be added across boards. Scores are rounded for display.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

From comparison to creation

Choose for your brief.

Test the exact words, hierarchy and aspect ratio you need. Check text at delivery size and inspect spacing rather than judging only the overall image. Plan editable final typography when the project needs precise brand control.

Compare your own image prompt

A source listing does not confirm current availability in Oakgen.

How this board is composed

Criteria and weights

Text accuracy17.5%
Layout17.5%
Subjective aesthetics7.5%
Creativity / variation7.5%
Reference adherence7.5%
Style adherence17.5%
Prompt adherence7.5%
Typography17.5%

Read the methodology