Benchmark Almanac

LMArena Image Edit Arena

GPT-Image-2.5 Sunburst 1,517 leads since Oct 2026 Not in model cards

Image editing models apply the same user edit request to the same image, anonymously and side by side. Community votes give Elo-style ratings.

Ratings are published in the image_edit config of the dataset.

Made by Arena (formerly LMArena) Released Jun 2025 Image generation and editing All tasks public Last model added Oct 2026 Scores refreshed 2 Nov 2026
Level
Everyday Most adults, without training
Scored
Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
Answers
Open-ended Free-form text, documents, designs or media judged as a whole.
Dataset Leaderboard arena.ai
57
Entries on its own leaderboard, 56 models we track

GPT-Image-2.5 Sunburst leads with 1,517

Best score per entry from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

57 entries. Scroll sideways for the rest. Bars start at 800.

  1. 1,517 GPT-Image-2.5 Sunburst
  2. 1,482 GPT-Image-2.5 Flare
  3. 1,471 MAI-Image-2.7-Preview
  4. 1,460 GPT-Image-2
  5. 1,439 Grok Imagine Image 2.0
  6. 1,427 MAI-Image-2.6
  7. 1,427 Gemini Nano Banana 2.1
  8. 1,411 Krea 3 Ultra
  9. 1,400 MAI-Image-2.5
  10. 1,400 Muse Image
  11. 1,391 Grok Imagine Image
  12. 1,390 Seedream 5.0 Pro
  13. 1,390 Gemini 3 Pro Image (nano-banana-pro, 2K)
  14. 1,387 Gemini 3.1 Flash Image (nano-banana-2, Web Search)
  15. 1,386 ChatGPT Image Latest
  16. 1,385 Gemini 3 Pro Image Preview (nano-banana-pro)
  17. 1,373 Reve 2.1
  18. 1,368 GPT-Image-1.5
  19. 1,362 Qwen-Image-2.1
  20. 1,358 Reve 2.0
  21. 1,347 Ideogram 4.5
  22. 1,334 UNI-1.1 Max
  23. 1,316 UNI-1.1
  24. 1,313 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)
  25. 1,303 Seedream 4.5
  26. 1,302 Qwen-Image-2.0-Pro
  27. 1,302 Wan 2.7 Image Pro
  28. 1,302 HunyuanImage 3.0 Instruct
  29. 1,301 Wan 2.7 Image
  30. 1,294 Seedream 5.0 Lite
  31. 1,291 Gemini 2.5 Flash Image Preview (nano-banana)
  32. 1,267 Seedream 4.0
  33. 1,261 FLUX.2 [max]
  34. 1,261 Reve v1.1
  35. 1,250 Kling Image O1
  36. 1,247 FLUX.2 [pro]
  37. 1,241 Qwen-Image-Edit
  38. 1,235 Reve v1
  39. 1,233 Qwen-Image-Edit (2511)
  40. 1,231 Wan 2.6 Image
  41. 1,224 FLUX.2 [flex]
  42. 1,224 FLUX.2 [klein] 9B
  43. 1,224 FLUX.2 [dev]
  44. 1,210 P-Image-Edit
  45. 1,207 Reve v1.1 Fast
  46. 1,198 Reve Edit Fast
  47. 1,187 FLUX.2 [klein] 4B
  48. 1,182 FLUX.1 Kontext [max]
  49. 1,180 Wan 2.5 Preview
  50. 1,177 FLUX.1 Kontext [pro]
  51. 1,151 FLUX.1 Kontext [dev]
  52. 1,139 SeedEdit 3.0
  53. 1,139 GPT-Image-1
  54. 1,124 GPT-Image-1 mini
  55. 1,082 Gemini 2.0 Flash Preview Image Generation
  56. 1,027 BAGEL
  57. 996 Step1X-Edit

Bars start at 800.

  1. 1 GPT-Image-2.5 Sunburst 1,517
  2. 2 GPT-Image-2.5 Flare 1,482
  3. 3 MAI-Image-2.7-Preview 1,471
  4. 4 GPT-Image-2 medium 1,460
  5. 5 Grok Imagine Image 2.0 1,439
  6. 6 MAI-Image-2.6 1,427
  7. 7 Gemini Nano Banana 2.1 1,427
  8. 8 Krea 3 Ultra 1,411
  9. 9 MAI-Image-2.5 1,400
  10. 10 Muse Image 1,400
  11. 11 Grok Imagine Image 1,391
  12. 12 Seedream 5.0 Pro 1,390
  13. 13 Gemini 3 Pro Image (nano-banana-pro, 2K) 1,390
  14. 14 Gemini 3.1 Flash Image (nano-banana-2, Web Search) 1,387
  15. 15 ChatGPT Image Latest high fidelity 1,386
  16. 16 Gemini 3 Pro Image Preview (nano-banana-pro) 1,385
  17. 17 Reve 2.1 1,373
  18. 18 GPT-Image-1.5 high fidelity 1,368
  19. 19 Qwen-Image-2.1 1,362
  20. 20 Reve 2.0 1,358
  21. 21 Ideogram 4.5 1,347
  22. 22 UNI-1.1 Max 1,334
  23. 23 UNI-1.1 1,316
  24. 24 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,313
  25. 25 Seedream 4.5 1,303
  26. 26 Qwen-Image-2.0-Pro 1,302
  27. 27 Wan 2.7 Image Pro 1,302
  28. 28 HunyuanImage 3.0 Instruct 1,302
  29. 29 Wan 2.7 Image 1,301
  30. 30 Seedream 5.0 Lite 1,294
  31. 31 Gemini 2.5 Flash Image Preview (nano-banana) 1,291
  32. 32 Seedream 4.0 1,267
  33. 33 FLUX.2 [max] 1,261
  34. 34 Reve v1.1 1,261
  35. 35 Kling Image O1 1,250
  36. 36 FLUX.2 [pro] 1,247
  37. 37 Qwen-Image-Edit 1,241
  38. 38 Reve v1 1,235
  39. 39 Qwen-Image-Edit (2511) 1,233
  40. 40 Wan 2.6 Image 1,231
  41. 41 FLUX.2 [flex] 1,224
  42. 42 FLUX.2 [klein] 9B 1,224
  43. 43 FLUX.2 [dev] 1,224
  44. 44 P-Image-Edit 1,210
  45. 45 Reve v1.1 Fast 1,207
  46. 46 Reve Edit Fast 1,198
  47. 47 FLUX.2 [klein] 4B 1,187
  48. 48 FLUX.1 Kontext [max] 1,182
  49. 49 Wan 2.5 Preview 1,180
  50. 50 FLUX.1 Kontext [pro] 1,177
  51. 51 FLUX.1 Kontext [dev] 1,151
  52. 52 SeedEdit 3.0 1,139
  53. 53 GPT-Image-1 1,139
  54. 54 GPT-Image-1 mini 1,124
  55. 55 Gemini 2.0 Flash Preview Image Generation 1,082
  56. 56 BAGEL 1,027
  57. 57 Step1X-Edit 996
#EntryScoreSettingDateSource
1 GPT-Image-2.5 Sunburst 1,517 Oct 2026 Official leaderboard
2 GPT-Image-2.5 Flare 1,482 Oct 2026 Official leaderboard
3 MAI-Image-2.7-Preview 1,471 Oct 2026 Official leaderboard
4 GPT-Image-2 1,460 medium Oct 2026 Official leaderboard
5 Grok Imagine Image 2.0 1,439 Oct 2026 Official leaderboard
6 MAI-Image-2.6 1,427 Oct 2026 Official leaderboard
7 Gemini Nano Banana 2.1 1,427 Oct 2026 Official leaderboard
8 Krea 3 Ultra 1,411 Oct 2026 Official leaderboard
9 MAI-Image-2.5 1,400 Oct 2026 Official leaderboard
10 Muse Image 1,400 Oct 2026 Official leaderboard
11 Grok Imagine Image 1,391 May 2026 Official leaderboard
12 Seedream 5.0 Pro 1,390 Oct 2026 Official leaderboard
13 Gemini 3 Pro Image (nano-banana-pro, 2K) 1,390 Oct 2026 Official leaderboard
14 Gemini 3.1 Flash Image (nano-banana-2, Web Search) 1,387 Oct 2026 Official leaderboard
15 ChatGPT Image Latest 1,386 high fidelity Dec 2025 Official leaderboard
16 Gemini 3 Pro Image Preview (nano-banana-pro) 1,385 Oct 2026 Official leaderboard
17 Reve 2.1 1,373 Oct 2026 Official leaderboard
18 GPT-Image-1.5 1,368 high fidelity Oct 2026 Official leaderboard
19 Qwen-Image-2.1 1,362 Oct 2026 Official leaderboard
20 Reve 2.0 1,358 Oct 2026 Official leaderboard
21 Ideogram 4.5 1,347 Oct 2026 Official leaderboard
22 UNI-1.1 Max 1,334 Oct 2026 Official leaderboard
23 UNI-1.1 1,316 Oct 2026 Official leaderboard
24 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,313 Oct 2026 Official leaderboard
25 Seedream 4.5 1,303 Oct 2026 Official leaderboard
26 Qwen-Image-2.0-Pro 1,302 Jun 2026 Official leaderboard
27 Wan 2.7 Image Pro 1,302 Oct 2026 Official leaderboard
28 HunyuanImage 3.0 Instruct 1,302 Oct 2026 Official leaderboard
29 Wan 2.7 Image 1,301 Oct 2026 Official leaderboard
30 Seedream 5.0 Lite 1,294 Oct 2026 Official leaderboard
31 Gemini 2.5 Flash Image Preview (nano-banana) 1,291 Oct 2026 Official leaderboard
32 Seedream 4.0 1,267 Oct 2026 Official leaderboard
33 FLUX.2 [max] 1,261 Oct 2026 Official leaderboard
34 Reve v1.1 1,261 Oct 2026 Official leaderboard
35 Kling Image O1 1,250 Oct 2026 Official leaderboard
36 FLUX.2 [pro] 1,247 Oct 2026 Official leaderboard
37 Qwen-Image-Edit 1,241 Oct 2026 Official leaderboard
38 Reve v1 1,235 Oct 2026 Official leaderboard
39 Qwen-Image-Edit (2511) 1,233 Oct 2026 Official leaderboard
40 Wan 2.6 Image 1,231 Oct 2026 Official leaderboard
41 FLUX.2 [flex] 1,224 Oct 2026 Official leaderboard
42 FLUX.2 [klein] 9B 1,224 Oct 2026 Official leaderboard
43 FLUX.2 [dev] 1,224 Oct 2026 Official leaderboard
44 P-Image-Edit 1,210 Oct 2026 Official leaderboard
45 Reve v1.1 Fast 1,207 Oct 2026 Official leaderboard
46 Reve Edit Fast 1,198 Oct 2026 Official leaderboard
47 FLUX.2 [klein] 4B 1,187 Oct 2026 Official leaderboard
48 FLUX.1 Kontext [max] 1,182 Oct 2026 Official leaderboard
49 Wan 2.5 Preview 1,180 Oct 2026 Official leaderboard
50 FLUX.1 Kontext [pro] 1,177 Oct 2026 Official leaderboard
51 FLUX.1 Kontext [dev] 1,151 Oct 2026 Official leaderboard
52 SeedEdit 3.0 1,139 Oct 2026 Official leaderboard
53 GPT-Image-1 1,139 Oct 2026 Official leaderboard
54 GPT-Image-1 mini 1,124 Oct 2026 Official leaderboard
55 Gemini 2.0 Flash Preview Image Generation 1,082 Oct 2026 Official leaderboard
56 BAGEL 1,027 Oct 2026 Official leaderboard
57 Step1X-Edit 996 Oct 2026 Official leaderboard

4 models have held number one since its release in Jun 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI xAI
Own leaderboard 4 leaders
GPT-Image-2.5 Sunburst 1,517

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
800 1,000 1,200 1,400 1,600 2026 2027 800 1,000 1,200 1,400 1,600 2026 2027

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Vision

All 234 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance. Command A Vision 90.9%
  • DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers. Seed1.5-VL 96.9%