Valumigo

LMArena · Photo-like images

We regularly fetch and display public benchmark data: LMArena user voting rankings, Epoch AI test scores, and OpenRouter usage rankings. Each leaderboard shows both its publication date and the date we retrieved it. These scores are not assigned by this site.

LMArena scores come from people comparing two models' answers side by side and voting for the better one, using an Elo-based system. If score differences fall within the confidence intervals, treat the models as roughly comparable.

How to read this leaderboard

What it measures: A ranking based on preference votes for image generation prompts requesting photographic or cinematic styles.

How to read the score: A relative score reflecting which images users preferred for these prompts. It does not separately score realism objectively.

Caveats: Compare models directly using the subjects and conditions you need, such as people, products or landscapes.

Insights from this ranking

  • The 95% confidence intervals for 1st-place gpt-image-2.5-sunburst and 2nd-place gpt-image-2.5-flare overlap. This aggregation alone does not clearly establish their order.
  • OpenAI has the most models among the top 10, with 3.
  • The 1st-place model received 3,918 votes, and this leaderboard includes 50 models.

Photo-like images LMArena

Published 2026-09-24 · Retrieved 2026-10-04

11901260133014001470
Ogpt-image-2.5-sunburst
1432
Ogpt-image-2.5-flare
1419
Ogpt-image-2 (medium)
1381
Mmai-image-2.6
1331
xgrok-imagine-image-2.0 (low)
1310
Rreve-2.1
1305
Metamuse-image
1286
ByteDanceseedream-5.0-pro
1280
Rreve-2.0
1279
Googlegemini-3.1-flash-image (nano-banana-2) [web-search]
1267
Alibabaqwen-image-3.0-pro
1263
Googlegemini-3-pro-image-2k (nano-banana-pro)
1261
Googlegemini-3.1-flash-lite-image (nano-banana-2-lite)
1260
Mmai-image-2.5
1252
Ogpt-image-1.5-high-fidelity
1249
Googlegemini-3-pro-image-preview (nano-banana-pro)
1245
Alibabaqwen-image-2.1
1235
Alibabaqwen-image-2.0-pro-2026-06-22
1209
Iideogram-4.0-quality
1204
Mmai-image-2
1204

Dots show scores; horizontal lines show 95% confidence intervals. Overlapping intervals suggest similar performance. The chart shows only the highest-scoring reasoning setting, such as high or max, for each model. The table shows rankings for all settings.

Top ranking by company

  • OOpenAIgpt-image-2.5-sunburst#1
  • MMicrosoft AImai-image-2.6#4
  • xxAIgrok-imagine-image-2.0 (low)#5
  • RRevereve-2.1#6
  • MetaMetamuse-image#7
  • ByteDanceByteDanceseedream-5.0-pro#8
  • GoogleGooglegemini-3.1-flash-image (nano-banana-2) [web-search]#10
  • AlibabaAlibabaqwen-image-3.0-pro#11
  • IIdeogramideogram-4.0-quality#19
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Ogpt-image-2.5-sunburstOpenAI14321420–14443,918
2#2Ogpt-image-2.5-flareOpenAI14191407–14323,469
3#3Ogpt-image-2 (medium)OpenAI13811375–138733,847
4#4Mmai-image-2.6Microsoft AI13311322–13406,713
5#5xgrok-imagine-image-2.0 (low)xAI13101298–13222,716
6#6Rreve-2.1Reve13051294–13153,348
7#7Metamuse-imageMeta12861279–129313,269
8#8ByteDanceseedream-5.0-proByteDance12801274–128633,043
9#9Rreve-2.0Reve12791271–12876,565
10#10Googlegemini-3.1-flash-image (nano-banana-2) [web-search]Google12671261–127321,007
11#11Alibabaqwen-image-3.0-proAlibaba12631253–12734,435
12#12Googlegemini-3-pro-image-2k (nano-banana-pro)Google12611257–126671,487
13#13Googlegemini-3.1-flash-lite-image (nano-banana-2-lite)Google12601251–12687,464
14#14Mmai-image-2.5Microsoft AI12521246–125823,780
15#15Ogpt-image-1.5-high-fidelityOpenAI12491245–125466,320
16#16Googlegemini-3-pro-image-preview (nano-banana-pro)Google12451239–125139,140
17#17Alibabaqwen-image-2.1Alibaba12351220–12491,653
18#18Alibabaqwen-image-2.0-pro-2026-06-22Alibaba12091200–12175,335
19#19Iideogram-4.0-qualityIdeogram12041198–121020,936
20#20Mmai-image-2Microsoft AI12041198–121020,925
21#21Luni-1.1-maxLuma AI11881180–11975,932
22#22Luni-1.1Luma AI11831177–118916,499
23#23Rrecraft-v4.1-utility-proRecraft11801162–11971,015
24#24xgrok-imagine-imagexAI11781174–1182107,871
25#25xgrok-imagine-image-proxAI11721166–117741,415
26#26NVIDIACosmos3-Super-Text2Image (Agentic)NVIDIA11671157–11764,209
27#27ByteDanceseedream-4.5ByteDance11661162–1170118,843
28#28Bflux-2-maxBlack Forest Labs11621157–116653,328
29#29Googlegemini-2.5-flash-image-preview (nano-banana)Google11571153–1160409,224
30#30ByteDanceseedream-5.0-liteByteDance11571152–116150,590
31#31Googleimagen-ultra-4.0-generate-001Google11551150–1161187,099
32#32Bflux-2-proBlack Forest Labs11521148–115687,103
33#33ByteDanceseedream-4-2kByteDance11511142–11605,930
34#34Thunyuan-image-3.0Tencent11511146–115580,874
35#35NVIDIACosmos3-Super-Text2ImageNVIDIA11501142–11597,192
36#36Rreve-v1.5Reve11491143–115516,226
37#37Rrecraft-v4.1-proRecraft11471130–11631,144
38#38Bflux-2-flexBlack Forest Labs11461141–115167,318
39#39Bflux-2-devBlack Forest Labs11431138–114933,046
40#40Googleimagen-4.0-generate-001Google11361132–1140251,359
41#41Alibabaqwen-image-2512Alibaba11351130–114042,042
42#42Kkrea-2-mediumKrea11331126–113919,586
43#43ByteDanceseedream-4-high-res-falByteDance11301126–113579,464
44#44Alibabawan2.6-t2iAlibaba11291125–113391,144
45#45Kkrea-2-largeKrea11261119–113219,240
46#46Alibabawan2.7-image-proAlibaba11231116–113011,959
47#47Kkrea-2-turboKrea11221115–112817,126
48#48ByteDanceseedream-4-falByteDance11211113–11305,656
49#49Rrecraft-v4Recraft11201115–112452,903
50#50Alibabaz-image-turboAlibaba11181111–112510,376

Data: LMArena leaderboard dataset (CC BY 4.0). Changes: Top 50 entries per leaderboard; scores are rounded. https://huggingface.co/datasets/lmarena-ai/leaderboard-datasetCompany logos are trademarks of their respective owners and are used only for identification (icons: Simple Icons).Data: Epoch AI — Capabilities & benchmarking (CC BY 4.0). https://epoch.ai/benchmarksSource: OpenRouter (openrouter.ai/rankings), as of 2026-10-04. Licensed under CC BY 4.0. https://openrouter.ai/rankings