Benchmark Almanac

DesignArena Logo

GPT-Image-2 1,365
Not in model cards

Image models design a logo from a user prompt. Users compare two anonymous logos and vote for the better one.

One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Image generation and editing
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Scores refreshed
November 12th, 2026
79
Entries on its own leaderboard, 44 models we track

GPT-Image-2 leads with 1,365

Best score per entry from the benchmark's own leaderboard, read on November 12th, 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.

79 entries. Scroll sideways for the rest. Bars start at 900.

  1. 1,365 GPT-Image-2
  2. 1,350 GPT-Image-2.5 Sunburst
  3. 1,339 Reve 2.1
  4. 1,329 Reve 2.0
  5. 1,302 GPT-Image-2.5 Flare
  6. 1,297 Riverflow 2.5 Pro
  7. 1,292 Grok Imagine Image 2.0
  8. 1,292 MAI-Image-2.6
  9. 1,282 GPT-Image-1.5
  10. 1,278 Nano Banana 2.1
  11. 1,268 MAI-Image-2.6 Flash
  12. 1,265 Ideogram 4.0
  13. 1,263 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2)
  14. 1,258 Qwen-Image-3.0-Pro
  15. 1,258 UNI-1.1 Max
  16. 1,257 Grok Imagine Image 2 Auto
  17. 1,248 MAI-Image-2.5
  18. 1,248 Gemini 3.1 Flash Image Gen (Nano Banana 2)
  19. 1,242 UNI-1.1
  20. 1,241 Seedream 5.0 Pro
  21. 1,241 Gemini 3 Pro Image Gen 2K (Nano Banana Pro)
  22. 1,236 Krea 2 Large
  23. 1,232 Muse Image
  24. 1,227 Recraft V4.1 Utility Pro
  25. 1,227 FLUX 3 Image
  26. 1,221 Krea 2 Medium
  27. 1,214 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)
  28. 1,209 FLUX.2 [flex]
  29. 1,209 GPT-Image-1 mini
  30. 1,207 Krea 2 Turbo
  31. 1,205 Recraft V4 Pro
  32. 1,203 ImagineArt 2.0
  33. 1,202 GPT-Image-1
  34. 1,193 Seedream Lite 5.0
  35. 1,192 FLUX.2 [pro]
  36. 1,191 Imagen 4 Ultra (generate-001)
  37. 1,191 Recraft V4.1 Pro
  38. 1,191 p-image-ideogram
  39. 1,186 FLUX.1 Kontext [max]
  40. 1,185 Imagen 4 Ultra Generate Preview 06-06
  41. 1,184 Wan 2.7 Pro
  42. 1,181 Gemini 3 Pro Image Preview
  43. 1,179 GLM-Image
  44. 1,177 Seedream 4.0
  45. 1,169 Boogu-Image-0.1
  46. 1,169 Gemini 2.5 Flash Image (Nano Banana)
  47. 1,167 Imagen 3 (generate-002)
  48. 1,166 Imagen 4 Generate Preview 06-06
  49. 1,165 Gemini 2.5 Flash Image Gen (Nano Banana)
  50. 1,164 Imagen 4 (generate-001)
  51. 1,164 Wan 2.7
  52. 1,163 Ideogram 3.0
  53. 1,161 Recraft V4.1
  54. 1,155 Recraft V4.1 Flash
  55. 1,154 Grok Imagine
  56. 1,149 FLUX.1 Kontext [pro]
  57. 1,143 FLUX.2 [dev]
  58. 1,135 Recraft V3
  59. 1,135 ERNIE Image
  60. 1,131 Reve Create
  61. 1,123 Qwen-Image (2512)
  62. 1,117 ERNIE Image Turbo
  63. 1,112 DALL-E 3
  64. 1,112 HunyuanImage 3.0
  65. 1,110 Cosmos 3 Super
  66. 1,106 Nucleus Image
  67. 1,103 Vidu Q2
  68. 1,092 FLUX.2 [klein] 9B
  69. 1,091 Z-Image-Turbo
  70. 1,076 FLUX.1 [pro] Ultra
  71. 1,063 Grok 2 Image Gen
  72. 1,060 FLUX.2 [klein] 4B
  73. 1,058 FLUX.2 Klein 4B Distilled
  74. 1,046 FLUX.1 Krea Dev
  75. 1,044 Qwen-Image
  76. 1,039 HiDream-O1-Image
  77. 1,034 Imagen 4 Fast Generate 001
  78. 1,011 HiDream O1 Image Dev
  79. 918 P-Image

Bars start at 900.

  1. 1 GPT-Image-2 1,365
  2. 2 GPT-Image-2.5 Sunburst 1,350
  3. 3 Reve 2.1 1,339
  4. 4 Reve 2.0 1,329
  5. 5 GPT-Image-2.5 Flare 1,302
  6. 6 Riverflow 2.5 Pro 1,297
  7. 7 Grok Imagine Image 2.0 medium 1,292
  8. 8 MAI-Image-2.6 1,292
  9. 9 GPT-Image-1.5 1,282
  10. 10 Nano Banana 2.1 1,278
  11. 11 MAI-Image-2.6 Flash 1,268
  12. 12 Ideogram 4.0 1,265
  13. 13 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2) 1,263
  14. 14 Qwen-Image-3.0-Pro 1,258
  15. 15 UNI-1.1 Max 1,258
  16. 16 Grok Imagine Image 2 Auto 1,257
  17. 17 MAI-Image-2.5 1,248
  18. 18 Gemini 3.1 Flash Image Gen (Nano Banana 2) 1,248
  19. 19 UNI-1.1 1,242
  20. 20 Seedream 5.0 Pro 1,241
  21. 21 Gemini 3 Pro Image Gen 2K (Nano Banana Pro) 1,241
  22. 22 Krea 2 Large 1,236
  23. 23 Muse Image 1,232
  24. 24 Recraft V4.1 Utility Pro 1,227
  25. 25 FLUX 3 Image 1,227
  26. 26 Krea 2 Medium 1,221
  27. 27 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,214
  28. 28 FLUX.2 [flex] 1,209
  29. 29 GPT-Image-1 mini 1,209
  30. 30 Krea 2 Turbo 1,207
  31. 31 Recraft V4 Pro 1,205
  32. 32 ImagineArt 2.0 1,203
  33. 33 GPT-Image-1 1,202
  34. 34 Seedream Lite 5.0 1,193
  35. 35 FLUX.2 [pro] 1,192
  36. 36 Imagen 4 Ultra (generate-001) 1,191
  37. 37 Recraft V4.1 Pro 1,191
  38. 38 p-image-ideogram medium, very high 1,191
  39. 39 FLUX.1 Kontext [max] 1,186
  40. 40 Imagen 4 Ultra Generate Preview 06-06 1,185
  41. 41 Wan 2.7 Pro 1,184
  42. 42 Gemini 3 Pro Image Preview 1,181
  43. 43 GLM-Image 1,179
  44. 44 Seedream 4.0 1,177
  45. 45 Boogu-Image-0.1 1,169
  46. 46 Gemini 2.5 Flash Image (Nano Banana) 1,169
  47. 47 Imagen 3 (generate-002) 1,167
  48. 48 Imagen 4 Generate Preview 06-06 1,166
  49. 49 Gemini 2.5 Flash Image Gen (Nano Banana) 1,165
  50. 50 Imagen 4 (generate-001) 1,164
  51. 51 Wan 2.7 1,164
  52. 52 Ideogram 3.0 1,163
  53. 53 Recraft V4.1 1,161
  54. 54 Recraft V4.1 Flash 1,155
  55. 55 Grok Imagine 1,154
  56. 56 FLUX.1 Kontext [pro] 1,149
  57. 57 FLUX.2 [dev] 1,143
  58. 58 Recraft V3 1,135
  59. 59 ERNIE Image 1,135
  60. 60 Reve Create 1,131
  61. 61 Qwen-Image (2512) 1,123
  62. 62 ERNIE Image Turbo 1,117
  63. 63 DALL-E 3 1,112
  64. 64 HunyuanImage 3.0 1,112
  65. 65 Cosmos 3 Super 1,110
  66. 66 Nucleus Image 1,106
  67. 67 Vidu Q2 1,103
  68. 68 FLUX.2 [klein] 9B 1,092
  69. 69 Z-Image-Turbo 1,091
  70. 70 FLUX.1 [pro] Ultra 1,076
  71. 71 Grok 2 Image Gen 1,063
  72. 72 FLUX.2 [klein] 4B 1,060
  73. 73 FLUX.2 Klein 4B Distilled 1,058
  74. 74 FLUX.1 Krea Dev 1,046
  75. 75 Qwen-Image 1,044
  76. 76 HiDream-O1-Image 1,039
  77. 77 Imagen 4 Fast Generate 001 1,034
  78. 78 HiDream O1 Image Dev 1,011
  79. 79 P-Image 918

Source: Official DesignArena Logo leaderboard

#EntryScoreSettingDateSource
1 GPT-Image-2 1,365 Official leaderboard
2 GPT-Image-2.5 Sunburst 1,350 Official leaderboard
3 Reve 2.1 1,339 Official leaderboard
4 Reve 2.0 1,329 Official leaderboard
5 GPT-Image-2.5 Flare 1,302 Official leaderboard
6 Riverflow 2.5 Pro 1,297 Official leaderboard
7 Grok Imagine Image 2.0 1,292 medium Official leaderboard
8 MAI-Image-2.6 1,292 Official leaderboard
9 GPT-Image-1.5 1,282 Official leaderboard
10 Nano Banana 2.1 1,278 Official leaderboard
11 MAI-Image-2.6 Flash 1,268 Official leaderboard
12 Ideogram 4.0 1,265 Official leaderboard
13 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2) 1,263 Official leaderboard
14 Qwen-Image-3.0-Pro 1,258 Official leaderboard
15 UNI-1.1 Max 1,258 Official leaderboard
16 Grok Imagine Image 2 Auto 1,257 Official leaderboard
17 MAI-Image-2.5 1,248 Official leaderboard
18 Gemini 3.1 Flash Image Gen (Nano Banana 2) 1,248 Official leaderboard
19 UNI-1.1 1,242 Official leaderboard
20 Seedream 5.0 Pro 1,241 Official leaderboard
21 Gemini 3 Pro Image Gen 2K (Nano Banana Pro) 1,241 Official leaderboard
22 Krea 2 Large 1,236 Official leaderboard
23 Muse Image 1,232 Official leaderboard
24 Recraft V4.1 Utility Pro 1,227 Official leaderboard
25 FLUX 3 Image 1,227 Official leaderboard
26 Krea 2 Medium 1,221 Official leaderboard
27 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,214 Official leaderboard
28 FLUX.2 [flex] 1,209 Official leaderboard
29 GPT-Image-1 mini 1,209 Official leaderboard
30 Krea 2 Turbo 1,207 Official leaderboard
31 Recraft V4 Pro 1,205 Official leaderboard
32 ImagineArt 2.0 1,203 Official leaderboard
33 GPT-Image-1 1,202 Official leaderboard
34 Seedream Lite 5.0 1,193 Official leaderboard
35 FLUX.2 [pro] 1,192 Official leaderboard
36 Imagen 4 Ultra (generate-001) 1,191 Official leaderboard
37 Recraft V4.1 Pro 1,191 Official leaderboard
38 p-image-ideogram 1,191 medium, very high Official leaderboard
39 FLUX.1 Kontext [max] 1,186 Official leaderboard
40 Imagen 4 Ultra Generate Preview 06-06 1,185 Official leaderboard
41 Wan 2.7 Pro 1,184 Official leaderboard
42 Gemini 3 Pro Image Preview 1,181 Official leaderboard
43 GLM-Image 1,179 Official leaderboard
44 Seedream 4.0 1,177 Official leaderboard
45 Boogu-Image-0.1 1,169 Official leaderboard
46 Gemini 2.5 Flash Image (Nano Banana) 1,169 Official leaderboard
47 Imagen 3 (generate-002) 1,167 Official leaderboard
48 Imagen 4 Generate Preview 06-06 1,166 Official leaderboard
49 Gemini 2.5 Flash Image Gen (Nano Banana) 1,165 Official leaderboard
50 Imagen 4 (generate-001) 1,164 Official leaderboard
51 Wan 2.7 1,164 Official leaderboard
52 Ideogram 3.0 1,163 Official leaderboard
53 Recraft V4.1 1,161 Official leaderboard
54 Recraft V4.1 Flash 1,155 Official leaderboard
55 Grok Imagine 1,154 Official leaderboard
56 FLUX.1 Kontext [pro] 1,149 Official leaderboard
57 FLUX.2 [dev] 1,143 Official leaderboard
58 Recraft V3 1,135 Official leaderboard
59 ERNIE Image 1,135 Official leaderboard
60 Reve Create 1,131 Official leaderboard
61 Qwen-Image (2512) 1,123 Official leaderboard
62 ERNIE Image Turbo 1,117 Official leaderboard
63 DALL-E 3 1,112 Official leaderboard
64 HunyuanImage 3.0 1,112 Official leaderboard
65 Cosmos 3 Super 1,110 Official leaderboard
66 Nucleus Image 1,106 Official leaderboard
67 Vidu Q2 1,103 Official leaderboard
68 FLUX.2 [klein] 9B 1,092 Official leaderboard
69 Z-Image-Turbo 1,091 Official leaderboard
70 FLUX.1 [pro] Ultra 1,076 Official leaderboard
71 Grok 2 Image Gen 1,063 Official leaderboard
72 FLUX.2 [klein] 4B 1,060 Official leaderboard
73 FLUX.2 Klein 4B Distilled 1,058 Official leaderboard
74 FLUX.1 Krea Dev 1,046 Official leaderboard
75 Qwen-Image 1,044 Official leaderboard
76 HiDream-O1-Image 1,039 Official leaderboard
77 Imagen 4 Fast Generate 001 1,034 Official leaderboard
78 HiDream O1 Image Dev 1,011 Official leaderboard
79 P-Image 918 Official leaderboard

Scores over time

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

No dated values yet.

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Vision

All 281 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. GPT-5.6 Sol 84.6%
  • 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%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
  • 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%