Benchmark Almanac

DesignArena Image

Not in model cards

Image models generate a picture from a user prompt. Users compare two anonymous images and vote for the better one.

Filters split it by subject, such as products, landscapes, architecture, typography and marketing. 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
Last model added
November 2026
Scores refreshed
November 12th, 2026
85
Entries on its own leaderboard, 46 models we track

GPT-Image-2.5 Sunburst leads with 1,386

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.

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

  1. 1,386 GPT-Image-2.5 Sunburst
  2. 1,384 GPT-Image-2.6 Sunburst
  3. 1,360 GPT-Image-2.5 Flare
  4. 1,357 GPT-Image-2.6 Flare
  5. 1,346 Riverflow 2.5 Pro
  6. 1,344 GPT-Image-2
  7. 1,305 Reve 2.1
  8. 1,303 Canva Craft
  9. 1,302 MAI-Image-2.6
  10. 1,296 Grok Imagine Image 2.0
  11. 1,293 Reve 2.0
  12. 1,290 MAI-Image-2.6 Flash
  13. 1,284 Nano Banana 2.1
  14. 1,275 Grok Imagine Image 2 Auto
  15. 1,266 GPT-Image-1.5
  16. 1,258 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2)
  17. 1,256 Qwen-Image-3.0-Pro
  18. 1,252 FLUX 3 Image
  19. 1,250 Gemini 3.1 Flash Image Gen (Nano Banana 2)
  20. 1,248 Muse Image
  21. 1,248 Seedream 5.0 Pro
  22. 1,225 Gemini 3 Pro Image Gen 2K (Nano Banana Pro)
  23. 1,221 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)
  24. 1,215 MAI-Image-2.5
  25. 1,213 Ideogram 4.0
  26. 1,207 MiniMax H3-Image
  27. 1,206 UNI-1.1 Max
  28. 1,197 Gemini 3 Pro Image Preview
  29. 1,196 UNI-1.1
  30. 1,194 Krea 2 Medium
  31. 1,192 Krea 2 Turbo
  32. 1,189 Krea 2 Large
  33. 1,183 Seedream Lite 5.0
  34. 1,181 FLUX.2 [flex]
  35. 1,177 FLUX.2 [pro]
  36. 1,175 Recraft V4.1 Utility Pro
  37. 1,175 Grok Imagine
  38. 1,174 Imagen 4 Ultra Generate Preview 06-06
  39. 1,173 GPT-Image-1
  40. 1,167 Imagen 4 Ultra (generate-001)
  41. 1,167 Gemini 2.5 Flash Image Gen (Nano Banana)
  42. 1,165 GPT-Image-1 mini
  43. 1,164 Seedream 4.0
  44. 1,162 p-image-ideogram
  45. 1,160 Gemini 2.5 Flash Image (Nano Banana)
  46. 1,157 FLUX 3 Image Klein
  47. 1,157 Imagen 4 Generate Preview 06-06
  48. 1,151 Wan 2.7 Pro
  49. 1,149 Imagen 4 (generate-001)
  50. 1,146 ImagineArt 2.0
  51. 1,145 Recraft V4.1 Pro
  52. 1,144 Recraft V4 Pro
  53. 1,140 Wan 2.7
  54. 1,138 Imagen 3 (generate-002)
  55. 1,136 FLUX.1 Kontext [max]
  56. 1,128 Recraft V4.1
  57. 1,112 HunyuanImage 3.0
  58. 1,111 FLUX.2 [dev]
  59. 1,105 Qwen-Image (2512)
  60. 1,101 Cosmos 3 Super
  61. 1,098 Boogu-Image-0.1
  62. 1,097 Recraft V4.1 Flash
  63. 1,096 FLUX.1 Kontext [pro]
  64. 1,096 Vidu Q2
  65. 1,092 FLUX.2 [klein] 9B
  66. 1,084 Recraft V3
  67. 1,082 GLM-Image
  68. 1,081 Z-Image-Turbo
  69. 1,075 Ideogram 3.0
  70. 1,068 ERNIE Image Turbo
  71. 1,065 ERNIE Image
  72. 1,057 Qwen-Image
  73. 1,057 FLUX.1 [pro] Ultra
  74. 1,052 Imagen 4 Fast Generate 001
  75. 1,049 DALL-E 3
  76. 1,045 FLUX.2 Klein 4B Distilled
  77. 1,044 FLUX.2 [klein] 4B
  78. 1,044 Reve Create
  79. 1,037 Nucleus Image
  80. 1,032 Gemini 2.0 Flash Image Gen (Preview)
  81. 1,028 HiDream-O1-Image
  82. 1,024 P-Image
  83. 1,014 FLUX.1 Krea Dev
  84. 1,010 Grok 2 Image Gen
  85. 991 HiDream O1 Image Dev

Bars start at 900.

  1. 1 GPT-Image-2.5 Sunburst 1,386
  2. 2 GPT-Image-2.6 Sunburst quality: max, complexity: high 1,384
  3. 3 GPT-Image-2.5 Flare 1,360
  4. 4 GPT-Image-2.6 Flare quality: auto, complexity: high 1,357
  5. 5 Riverflow 2.5 Pro 1,346
  6. 6 GPT-Image-2 1,344
  7. 7 Reve 2.1 1,305
  8. 8 Canva Craft 1,303
  9. 9 MAI-Image-2.6 1,302
  10. 10 Grok Imagine Image 2.0 medium 1,296
  11. 11 Reve 2.0 1,293
  12. 12 MAI-Image-2.6 Flash 1,290
  13. 13 Nano Banana 2.1 1,284
  14. 14 Grok Imagine Image 2 Auto 1,275
  15. 15 GPT-Image-1.5 1,266
  16. 16 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2) 1,258
  17. 17 Qwen-Image-3.0-Pro 1,256
  18. 18 FLUX 3 Image 1,252
  19. 19 Gemini 3.1 Flash Image Gen (Nano Banana 2) 1,250
  20. 20 Muse Image 1,248
  21. 21 Seedream 5.0 Pro 1,248
  22. 22 Gemini 3 Pro Image Gen 2K (Nano Banana Pro) 1,225
  23. 23 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,221
  24. 24 MAI-Image-2.5 1,215
  25. 25 Ideogram 4.0 1,213
  26. 26 MiniMax H3-Image 1,207
  27. 27 UNI-1.1 Max 1,206
  28. 28 Gemini 3 Pro Image Preview 1,197
  29. 29 UNI-1.1 1,196
  30. 30 Krea 2 Medium 1,194
  31. 31 Krea 2 Turbo 1,192
  32. 32 Krea 2 Large 1,189
  33. 33 Seedream Lite 5.0 1,183
  34. 34 FLUX.2 [flex] 1,181
  35. 35 FLUX.2 [pro] 1,177
  36. 36 Recraft V4.1 Utility Pro 1,175
  37. 37 Grok Imagine 1,175
  38. 38 Imagen 4 Ultra Generate Preview 06-06 1,174
  39. 39 GPT-Image-1 1,173
  40. 40 Imagen 4 Ultra (generate-001) 1,167
  41. 41 Gemini 2.5 Flash Image Gen (Nano Banana) 1,167
  42. 42 GPT-Image-1 mini 1,165
  43. 43 Seedream 4.0 1,164
  44. 44 p-image-ideogram medium, high 1,162
  45. 45 Gemini 2.5 Flash Image (Nano Banana) 1,160
  46. 46 FLUX 3 Image Klein 1,157
  47. 47 Imagen 4 Generate Preview 06-06 1,157
  48. 48 Wan 2.7 Pro 1,151
  49. 49 Imagen 4 (generate-001) 1,149
  50. 50 ImagineArt 2.0 1,146
  51. 51 Recraft V4.1 Pro 1,145
  52. 52 Recraft V4 Pro 1,144
  53. 53 Wan 2.7 1,140
  54. 54 Imagen 3 (generate-002) 1,138
  55. 55 FLUX.1 Kontext [max] 1,136
  56. 56 Recraft V4.1 1,128
  57. 57 HunyuanImage 3.0 1,112
  58. 58 FLUX.2 [dev] 1,111
  59. 59 Qwen-Image (2512) 1,105
  60. 60 Cosmos 3 Super 1,101
  61. 61 Boogu-Image-0.1 1,098
  62. 62 Recraft V4.1 Flash 1,097
  63. 63 FLUX.1 Kontext [pro] 1,096
  64. 64 Vidu Q2 1,096
  65. 65 FLUX.2 [klein] 9B 1,092
  66. 66 Recraft V3 1,084
  67. 67 GLM-Image 1,082
  68. 68 Z-Image-Turbo 1,081
  69. 69 Ideogram 3.0 1,075
  70. 70 ERNIE Image Turbo 1,068
  71. 71 ERNIE Image 1,065
  72. 72 Qwen-Image 1,057
  73. 73 FLUX.1 [pro] Ultra 1,057
  74. 74 Imagen 4 Fast Generate 001 1,052
  75. 75 DALL-E 3 1,049
  76. 76 FLUX.2 Klein 4B Distilled 1,045
  77. 77 FLUX.2 [klein] 4B 1,044
  78. 78 Reve Create 1,044
  79. 79 Nucleus Image 1,037
  80. 80 Gemini 2.0 Flash Image Gen (Preview) 1,032
  81. 81 HiDream-O1-Image 1,028
  82. 82 P-Image 1,024
  83. 83 FLUX.1 Krea Dev 1,014
  84. 84 Grok 2 Image Gen 1,010
  85. 85 HiDream O1 Image Dev 991

Source: Official DesignArena Image leaderboard

#EntryScoreSettingDateSource
1 GPT-Image-2.5 Sunburst 1,386 Official leaderboard
2 GPT-Image-2.6 Sunburst 1,384 quality: max, complexity: high Nov 2026 Official leaderboard
3 GPT-Image-2.5 Flare 1,360 Official leaderboard
4 GPT-Image-2.6 Flare 1,357 quality: auto, complexity: high Nov 2026 Official leaderboard
5 Riverflow 2.5 Pro 1,346 Official leaderboard
6 GPT-Image-2 1,344 Official leaderboard
7 Reve 2.1 1,305 Official leaderboard
8 Canva Craft 1,303 Official leaderboard
9 MAI-Image-2.6 1,302 Official leaderboard
10 Grok Imagine Image 2.0 1,296 medium Official leaderboard
11 Reve 2.0 1,293 Official leaderboard
12 MAI-Image-2.6 Flash 1,290 Official leaderboard
13 Nano Banana 2.1 1,284 Official leaderboard
14 Grok Imagine Image 2 Auto 1,275 Official leaderboard
15 GPT-Image-1.5 1,266 Official leaderboard
16 Gemini 3.1 Flash Image Gen 2K (Nano Banana 2) 1,258 Official leaderboard
17 Qwen-Image-3.0-Pro 1,256 Official leaderboard
18 FLUX 3 Image 1,252 Official leaderboard
19 Gemini 3.1 Flash Image Gen (Nano Banana 2) 1,250 Official leaderboard
20 Muse Image 1,248 Official leaderboard
21 Seedream 5.0 Pro 1,248 Official leaderboard
22 Gemini 3 Pro Image Gen 2K (Nano Banana Pro) 1,225 Official leaderboard
23 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,221 Official leaderboard
24 MAI-Image-2.5 1,215 Official leaderboard
25 Ideogram 4.0 1,213 Official leaderboard
26 MiniMax H3-Image 1,207 Official leaderboard
27 UNI-1.1 Max 1,206 Official leaderboard
28 Gemini 3 Pro Image Preview 1,197 Official leaderboard
29 UNI-1.1 1,196 Official leaderboard
30 Krea 2 Medium 1,194 Official leaderboard
31 Krea 2 Turbo 1,192 Official leaderboard
32 Krea 2 Large 1,189 Official leaderboard
33 Seedream Lite 5.0 1,183 Official leaderboard
34 FLUX.2 [flex] 1,181 Official leaderboard
35 FLUX.2 [pro] 1,177 Official leaderboard
36 Recraft V4.1 Utility Pro 1,175 Official leaderboard
37 Grok Imagine 1,175 Official leaderboard
38 Imagen 4 Ultra Generate Preview 06-06 1,174 Official leaderboard
39 GPT-Image-1 1,173 Official leaderboard
40 Imagen 4 Ultra (generate-001) 1,167 Official leaderboard
41 Gemini 2.5 Flash Image Gen (Nano Banana) 1,167 Official leaderboard
42 GPT-Image-1 mini 1,165 Official leaderboard
43 Seedream 4.0 1,164 Official leaderboard
44 p-image-ideogram 1,162 medium, high Official leaderboard
45 Gemini 2.5 Flash Image (Nano Banana) 1,160 Official leaderboard
46 FLUX 3 Image Klein 1,157 Official leaderboard
47 Imagen 4 Generate Preview 06-06 1,157 Official leaderboard
48 Wan 2.7 Pro 1,151 Official leaderboard
49 Imagen 4 (generate-001) 1,149 Official leaderboard
50 ImagineArt 2.0 1,146 Official leaderboard
51 Recraft V4.1 Pro 1,145 Official leaderboard
52 Recraft V4 Pro 1,144 Official leaderboard
53 Wan 2.7 1,140 Official leaderboard
54 Imagen 3 (generate-002) 1,138 Official leaderboard
55 FLUX.1 Kontext [max] 1,136 Official leaderboard
56 Recraft V4.1 1,128 Official leaderboard
57 HunyuanImage 3.0 1,112 Official leaderboard
58 FLUX.2 [dev] 1,111 Official leaderboard
59 Qwen-Image (2512) 1,105 Official leaderboard
60 Cosmos 3 Super 1,101 Official leaderboard
61 Boogu-Image-0.1 1,098 Official leaderboard
62 Recraft V4.1 Flash 1,097 Official leaderboard
63 FLUX.1 Kontext [pro] 1,096 Official leaderboard
64 Vidu Q2 1,096 Official leaderboard
65 FLUX.2 [klein] 9B 1,092 Official leaderboard
66 Recraft V3 1,084 Official leaderboard
67 GLM-Image 1,082 Official leaderboard
68 Z-Image-Turbo 1,081 Official leaderboard
69 Ideogram 3.0 1,075 Official leaderboard
70 ERNIE Image Turbo 1,068 Official leaderboard
71 ERNIE Image 1,065 Official leaderboard
72 Qwen-Image 1,057 Official leaderboard
73 FLUX.1 [pro] Ultra 1,057 Official leaderboard
74 Imagen 4 Fast Generate 001 1,052 Official leaderboard
75 DALL-E 3 1,049 Official leaderboard
76 FLUX.2 Klein 4B Distilled 1,045 Official leaderboard
77 FLUX.2 [klein] 4B 1,044 Official leaderboard
78 Reve Create 1,044 Official leaderboard
79 Nucleus Image 1,037 Official leaderboard
80 Gemini 2.0 Flash Image Gen (Preview) 1,032 Official leaderboard
81 HiDream-O1-Image 1,028 Official leaderboard
82 P-Image 1,024 Official leaderboard
83 FLUX.1 Krea Dev 1,014 Official leaderboard
84 Grok 2 Image Gen 1,010 Official leaderboard
85 HiDream O1 Image Dev 991 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard 1 leader

Source: Official DesignArena Image leaderboard

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
1,300 1,320 1,340 1,360 1,380 1,400 2027 1,300 1,320 1,340 1,360 1,380 1,400 2027

Source: Official DesignArena Image leaderboard

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%