The creative model reference

AI image models for film concepts

Reference rankings for cinematic imagery, story development and film concepts.

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

image / Film

The scores, in perspective.

7 models · 95% intervals

Swipe to compare all models →

Oakgen Arena · v1.0

11,074

Seedream 5.0 Pro

21,059

Nano Banana Pro

31,058

GPT Image 2

41,000

Grok Imagine 2.0Anchor

5998

Nano Banana 2

6978

Flux.2 Pro

7964

Qwen Image 3.0

↥ 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

Film leaderboard

Film image rankings · Benchmark index 1.0
Rank	Model	Overall score	95% confidence interval	Vote appearances	Distinct judges
01	Seedream 5.0 ProByteDance Criterion scores Creativity / variation1,102.695% CI 1,050.6 to 1,156.5Reused fit from master-image Film texture1,070.195% CI 983.6 to 1,163.6 Prompt adherence1,022.295% CI 982.2 to 1,060.8Reused fit from master-image Realism1,141.995% CI 1,070.7 to 1,209.5 Reference adherence1,036.795% CI 988.2 to 1,080Reused fit from master-image Scene setup and lighting1,038.295% CI 958.5 to 1,126.7 Subjective aesthetics1,042.895% CI 990.5 to 1,095.7Reused fit from master-image	1,073.7LEAD	1,041 to 1,106.4	2,604	Not reported
02	Nano Banana ProGoogle Criterion scores Creativity / variation1,032.295% CI 978.2 to 1,084.8Reused fit from master-image Film texture1,057.395% CI 975.7 to 1,128.9 Prompt adherence1,018.395% CI 978.4 to 1,058.1Reused fit from master-image Realism1,18495% CI 1,112.9 to 1,259.2 Reference adherence1,002.295% CI 948.1 to 1,052.2Reused fit from master-image Scene setup and lighting1,002.895% CI 913.9 to 1,096.7 Subjective aesthetics981.195% CI 930.5 to 1,027.6Reused fit from master-image	1,059.5#2	1,025.4 to 1,091.9	2,622	Not reported
03	GPT Image 2OpenAI Criterion scores Creativity / variation1,081.995% CI 1,037.4 to 1,128.3Reused fit from master-image Film texture1,089.295% CI 996.3 to 1,187.3 Prompt adherence1,041.595% CI 1,010.7 to 1,074.8Reused fit from master-image Realism1,058.295% CI 993.2 to 1,124.1 Reference adherence1,035.395% CI 987 to 1,083.2Reused fit from master-image Scene setup and lighting1,041.795% CI 977.2 to 1,111.2 Subjective aesthetics1,030.195% CI 987.2 to 1,071.2Reused fit from master-image	1,058.3#3	1,027.5 to 1,089.4	2,583	Not reported
04	Grok Imagine 2.0xAI Criterion scores Creativity / variation1,00095% CI Anchor · interval not reportedReused fit from master-image Film texture1,00095% CI Anchor · interval not reported Prompt adherence1,00095% CI Anchor · interval not reportedReused fit from master-image Realism1,00095% CI Anchor · interval not reported Reference adherence1,00095% CI Anchor · interval not reportedReused fit from master-image Scene setup and lighting1,00095% CI Anchor · interval not reported Subjective aesthetics1,00095% CI Anchor · interval not reportedReused fit from master-image	1,000Anchor	Anchor · interval not reported	2,617	Not reported
05	Nano Banana 2Google Criterion scores Creativity / variation972.695% CI 913.5 to 1,028.8Reused fit from master-image Film texture982.895% CI 876.9 to 1,086.2 Prompt adherence977.395% CI 937.4 to 1,017.6Reused fit from master-image Realism1,063.695% CI 978.5 to 1,142.5 Reference adherence990.895% CI 945.5 to 1,039.8Reused fit from master-image Scene setup and lighting962.195% CI 877.5 to 1,046.4 Subjective aesthetics1,000.495% CI 954 to 1,052.4Reused fit from master-image	997.6	958.7 to 1,030.3	2,616	Not reported
06	Flux.2 ProBlack Forest Labs Criterion scores Creativity / variation909.695% CI 857.1 to 961.2Reused fit from master-image Film texture1,023.195% CI 951.3 to 1,106.7 Prompt adherence940.995% CI 907.8 to 976.6Reused fit from master-image Realism1,021.695% CI 964 to 1,077.8 Reference adherence881.195% CI 833.9 to 927.5Reused fit from master-image Scene setup and lighting953.495% CI 870.9 to 1,035.2 Subjective aesthetics977.795% CI 921.3 to 1,028.8Reused fit from master-image	977.7	947.6 to 1,006.7	2,613	Not reported
07	Qwen Image 3.0Alibaba Criterion scores Creativity / variation997.195% CI 949.8 to 1,047.1Reused fit from master-image Film texture972.395% CI 903.2 to 1,032.5 Prompt adherence915.195% CI 880.5 to 949.6Reused fit from master-image Realism974.995% CI 894.6 to 1,047.2 Reference adherence973.295% CI 921.3 to 1,028.5Reused fit from master-image Scene setup and lighting941.595% CI 849.2 to 1,035.2 Subjective aesthetics979.495% CI 928.4 to 1,035.8Reused fit from master-image	963.9	929.3 to 997.3	2,613	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.

Use a consistent brief for lens feel, composition and lighting. For storyboards, test whether the subject and environment stay coherent across frames. A beautiful concept image can still need substantial work before it becomes a usable production reference.

Compare your own image prompt

A source listing does not confirm current availability in Oakgen.

How this board is composed

Criteria and weights

Scene setup and lighting23.3%
Realism23.3%
Film texture23.3%
Prompt adherence7.5%
Subjective aesthetics7.5%
Creativity / variation7.5%
Reference adherence7.5%

Read the methodology