Benchmark Almanac

LMArena Text-to-Image Arena

GPT-Image-2.5 Sunburst 1,427 leads since Oct 2026 Not in model cards

Image generation models answer the same user prompt side by side and anonymously. Community votes between the two images give Elo-style ratings.

LMArena announced the arena in December 2024 and opened the leaderboard in January 2025, per posts found in search. Ratings are in the text_to_image config of the dataset.

Made by Arena (formerly LMArena) Released Dec 2024 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.
77
Entries on its own leaderboard, 76 models we track

GPT-Image-2.5 Sunburst leads with 1,427

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.

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

  1. 1,427 GPT-Image-2.5 Sunburst
  2. 1,401 GPT-Image-2.5 Flare
  3. 1,381 GPT-Image-2
  4. 1,329 MAI-Image-2.6
  5. 1,325 Gemini Nano Banana 2.1
  6. 1,317 Grok Imagine Image 2.0
  7. 1,300 Reve 2.1
  8. 1,269 Muse Image
  9. 1,268 Reve 2.0
  10. 1,257 Gemini 3.1 Flash Image (nano-banana-2, Web Search)
  11. 1,254 Qwen-Image-3.0-Pro
  12. 1,253 MAI-Image-2.5
  13. 1,250 Seedream 5.0 Pro
  14. 1,249 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)
  15. 1,246 Gemini 3 Pro Image (nano-banana-pro, 2K)
  16. 1,236 GPT-Image-1.5
  17. 1,232 Gemini 3 Pro Image Preview (nano-banana-pro)
  18. 1,225 Qwen-Image-2.1
  19. 1,200 Ideogram 4.0
  20. 1,191 Qwen-Image-2.0-Pro
  21. 1,189 UNI-1.1 Max
  22. 1,183 MAI-Image-2
  23. 1,183 UNI-1.1
  24. 1,169 Grok Imagine Image
  25. 1,168 Recraft V4.1 Utility Pro
  26. 1,164 Cosmos3-Super-Text2Image
  27. 1,161 FLUX.2 [max]
  28. 1,161 Grok Imagine Image Pro
  29. 1,156 FLUX.2 [flex]
  30. 1,154 Reve v1.5
  31. 1,153 FLUX.2 [pro]
  32. 1,151 HunyuanImage 3.0
  33. 1,149 Seedream 4.5
  34. 1,149 Gemini 2.5 Flash Image Preview (nano-banana)
  35. 1,146 Imagen 4 Ultra (generate-001)
  36. 1,145 FLUX.2 [dev]
  37. 1,140 Seedream 5.0 Lite
  38. 1,139 Seedream 4.0
  39. 1,138 Wan 2.6
  40. 1,131 Recraft V4.1 Pro
  41. 1,128 Imagen 4 (generate-001)
  42. 1,128 Krea 2 Medium
  43. 1,125 Qwen-Image (2512)
  44. 1,117 Wan 2.5 Preview
  45. 1,115 Krea 2 Large
  46. 1,115 GPT-Image-1
  47. 1,115 Recraft V4
  48. 1,115 HiDream-O1-Image
  49. 1,114 Krea 2 Turbo
  50. 1,109 GPT-Image-1 mini
  51. 1,103 Wan 2.7 Image Pro
  52. 1,101 Wan 2.7 Image
  53. 1,098 Recraft V4.1 Flash
  54. 1,092 MAI-Image-1
  55. 1,082 Z-Image-Turbo
  56. 1,082 Seedream 3.0
  57. 1,075 FLUX.1 Kontext [max]
  58. 1,070 FLUX.2 [klein] 9B
  59. 1,061 Qwen-Image
  60. 1,059 FLUX.1 Kontext [pro]
  61. 1,057 Imagen 3 (generate-002)
  62. 1,049 Ideogram 3.0
  63. 1,036 Luma Photon
  64. 1,032 P-Image
  65. 1,030 FLUX.2 [klein] 4B
  66. 1,024 Runway Gen-4
  67. 1,022 Recraft V3
  68. 1,016 FLUX1.1 [pro]
  69. 1,013 Ideogram 2.0
  70. 1,013 Lucid Origin
  71. 1,012 GLM-Image
  72. 976 Gemini 2.0 Flash Preview Image Generation
  73. 969 FLUX.1 [dev]
  74. 967 DALL-E 3
  75. 942 FLUX.1 Kontext [dev]
  76. 938 Stable Diffusion 3.5 Large
  77. 897 BAGEL

Bars start at 800.

  1. 1 GPT-Image-2.5 Sunburst 1,427
  2. 2 GPT-Image-2.5 Flare 1,401
  3. 3 GPT-Image-2 medium 1,381
  4. 4 MAI-Image-2.6 1,329
  5. 5 Gemini Nano Banana 2.1 1,325
  6. 6 Grok Imagine Image 2.0 1,317
  7. 7 Reve 2.1 1,300
  8. 8 Muse Image 1,269
  9. 9 Reve 2.0 1,268
  10. 10 Gemini 3.1 Flash Image (nano-banana-2, Web Search) 1,257
  11. 11 Qwen-Image-3.0-Pro 1,254
  12. 12 MAI-Image-2.5 1,253
  13. 13 Seedream 5.0 Pro 1,250
  14. 14 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,249
  15. 15 Gemini 3 Pro Image (nano-banana-pro, 2K) 1,246
  16. 16 GPT-Image-1.5 high fidelity 1,236
  17. 17 Gemini 3 Pro Image Preview (nano-banana-pro) 1,232
  18. 18 Qwen-Image-2.1 1,225
  19. 19 Ideogram 4.0 1,200
  20. 20 Qwen-Image-2.0-Pro 1,191
  21. 21 UNI-1.1 Max 1,189
  22. 22 MAI-Image-2 1,183
  23. 23 UNI-1.1 1,183
  24. 24 Grok Imagine Image 1,169
  25. 25 Recraft V4.1 Utility Pro 1,168
  26. 26 Cosmos3-Super-Text2Image 1,164
  27. 27 FLUX.2 [max] 1,161
  28. 28 Grok Imagine Image Pro 1,161
  29. 29 FLUX.2 [flex] 1,156
  30. 30 Reve v1.5 1,154
  31. 31 FLUX.2 [pro] 1,153
  32. 32 HunyuanImage 3.0 1,151
  33. 33 Seedream 4.5 1,149
  34. 34 Gemini 2.5 Flash Image Preview (nano-banana) 1,149
  35. 35 Imagen 4 Ultra (generate-001) 1,146
  36. 36 FLUX.2 [dev] 1,145
  37. 37 Seedream 5.0 Lite 1,140
  38. 38 Seedream 4.0 1,139
  39. 39 Wan 2.6 1,138
  40. 40 Recraft V4.1 Pro 1,131
  41. 41 Imagen 4 (generate-001) 1,128
  42. 42 Krea 2 Medium 1,128
  43. 43 Qwen-Image (2512) 1,125
  44. 44 Wan 2.5 Preview 1,117
  45. 45 Krea 2 Large 1,115
  46. 46 GPT-Image-1 1,115
  47. 47 Recraft V4 1,115
  48. 48 HiDream-O1-Image 1,115
  49. 49 Krea 2 Turbo 1,114
  50. 50 GPT-Image-1 mini 1,109
  51. 51 Wan 2.7 Image Pro 1,103
  52. 52 Wan 2.7 Image 1,101
  53. 53 Recraft V4.1 Flash 1,098
  54. 54 MAI-Image-1 1,092
  55. 55 Z-Image-Turbo 1,082
  56. 56 Seedream 3.0 1,082
  57. 57 FLUX.1 Kontext [max] 1,075
  58. 58 FLUX.2 [klein] 9B 1,070
  59. 59 Qwen-Image 1,061
  60. 60 FLUX.1 Kontext [pro] 1,059
  61. 61 Imagen 3 (generate-002) 1,057
  62. 62 Ideogram 3.0 1,049
  63. 63 Luma Photon 1,036
  64. 64 P-Image 1,032
  65. 65 FLUX.2 [klein] 4B 1,030
  66. 66 Runway Gen-4 1,024
  67. 67 Recraft V3 1,022
  68. 68 FLUX1.1 [pro] 1,016
  69. 69 Ideogram 2.0 1,013
  70. 70 Lucid Origin 1,013
  71. 71 GLM-Image 1,012
  72. 72 Gemini 2.0 Flash Preview Image Generation 976
  73. 73 FLUX.1 [dev] fp8 969
  74. 74 DALL-E 3 967
  75. 75 FLUX.1 Kontext [dev] 942
  76. 76 Stable Diffusion 3.5 Large 938
  77. 77 BAGEL 897
#EntryScoreSettingDateSource
1 GPT-Image-2.5 Sunburst 1,427 Oct 2026 Official leaderboard
2 GPT-Image-2.5 Flare 1,401 Oct 2026 Official leaderboard
3 GPT-Image-2 1,381 medium Oct 2026 Official leaderboard
4 MAI-Image-2.6 1,329 Oct 2026 Official leaderboard
5 Gemini Nano Banana 2.1 1,325 Oct 2026 Official leaderboard
6 Grok Imagine Image 2.0 1,317 Oct 2026 Official leaderboard
7 Reve 2.1 1,300 Oct 2026 Official leaderboard
8 Muse Image 1,269 Oct 2026 Official leaderboard
9 Reve 2.0 1,268 Oct 2026 Official leaderboard
10 Gemini 3.1 Flash Image (nano-banana-2, Web Search) 1,257 Oct 2026 Official leaderboard
11 Qwen-Image-3.0-Pro 1,254 Oct 2026 Official leaderboard
12 MAI-Image-2.5 1,253 Oct 2026 Official leaderboard
13 Seedream 5.0 Pro 1,250 Oct 2026 Official leaderboard
14 Gemini 3.1 Flash-Lite Image (nano-banana-2-lite) 1,249 Oct 2026 Official leaderboard
15 Gemini 3 Pro Image (nano-banana-pro, 2K) 1,246 Oct 2026 Official leaderboard
16 GPT-Image-1.5 1,236 high fidelity Oct 2026 Official leaderboard
17 Gemini 3 Pro Image Preview (nano-banana-pro) 1,232 Oct 2026 Official leaderboard
18 Qwen-Image-2.1 1,225 Oct 2026 Official leaderboard
19 Ideogram 4.0 1,200 Oct 2026 Official leaderboard
20 Qwen-Image-2.0-Pro 1,191 Jun 2026 Official leaderboard
21 UNI-1.1 Max 1,189 Oct 2026 Official leaderboard
22 MAI-Image-2 1,183 Oct 2026 Official leaderboard
23 UNI-1.1 1,183 Oct 2026 Official leaderboard
24 Grok Imagine Image 1,169 Oct 2026 Official leaderboard
25 Recraft V4.1 Utility Pro 1,168 Oct 2026 Official leaderboard
26 Cosmos3-Super-Text2Image 1,164 Oct 2026 Official leaderboard
27 FLUX.2 [max] 1,161 Oct 2026 Official leaderboard
28 Grok Imagine Image Pro 1,161 Oct 2026 Official leaderboard
29 FLUX.2 [flex] 1,156 Oct 2026 Official leaderboard
30 Reve v1.5 1,154 Oct 2026 Official leaderboard
31 FLUX.2 [pro] 1,153 Oct 2026 Official leaderboard
32 HunyuanImage 3.0 1,151 Oct 2026 Official leaderboard
33 Seedream 4.5 1,149 Oct 2026 Official leaderboard
34 Gemini 2.5 Flash Image Preview (nano-banana) 1,149 Oct 2026 Official leaderboard
35 Imagen 4 Ultra (generate-001) 1,146 Oct 2026 Official leaderboard
36 FLUX.2 [dev] 1,145 Oct 2026 Official leaderboard
37 Seedream 5.0 Lite 1,140 Oct 2026 Official leaderboard
38 Seedream 4.0 1,139 Oct 2026 Official leaderboard
39 Wan 2.6 1,138 Oct 2026 Official leaderboard
40 Recraft V4.1 Pro 1,131 Oct 2026 Official leaderboard
41 Imagen 4 (generate-001) 1,128 Oct 2026 Official leaderboard
42 Krea 2 Medium 1,128 Oct 2026 Official leaderboard
43 Qwen-Image (2512) 1,125 Oct 2026 Official leaderboard
44 Wan 2.5 Preview 1,117 Oct 2026 Official leaderboard
45 Krea 2 Large 1,115 Oct 2026 Official leaderboard
46 GPT-Image-1 1,115 Oct 2026 Official leaderboard
47 Recraft V4 1,115 Oct 2026 Official leaderboard
48 HiDream-O1-Image 1,115 Oct 2026 Official leaderboard
49 Krea 2 Turbo 1,114 Oct 2026 Official leaderboard
50 GPT-Image-1 mini 1,109 Oct 2026 Official leaderboard
51 Wan 2.7 Image Pro 1,103 Oct 2026 Official leaderboard
52 Wan 2.7 Image 1,101 Oct 2026 Official leaderboard
53 Recraft V4.1 Flash 1,098 Oct 2026 Official leaderboard
54 MAI-Image-1 1,092 Oct 2026 Official leaderboard
55 Z-Image-Turbo 1,082 Oct 2026 Official leaderboard
56 Seedream 3.0 1,082 Oct 2026 Official leaderboard
57 FLUX.1 Kontext [max] 1,075 Oct 2026 Official leaderboard
58 FLUX.2 [klein] 9B 1,070 Oct 2026 Official leaderboard
59 Qwen-Image 1,061 Oct 2026 Official leaderboard
60 FLUX.1 Kontext [pro] 1,059 Oct 2026 Official leaderboard
61 Imagen 3 (generate-002) 1,057 Oct 2026 Official leaderboard
62 Ideogram 3.0 1,049 Oct 2026 Official leaderboard
63 Luma Photon 1,036 Oct 2026 Official leaderboard
64 P-Image 1,032 Oct 2026 Official leaderboard
65 FLUX.2 [klein] 4B 1,030 Oct 2026 Official leaderboard
66 Runway Gen-4 1,024 Oct 2026 Official leaderboard
67 Recraft V3 1,022 Oct 2026 Official leaderboard
68 FLUX1.1 [pro] 1,016 Oct 2026 Official leaderboard
69 Ideogram 2.0 1,013 Oct 2026 Official leaderboard
70 Lucid Origin 1,013 Oct 2026 Official leaderboard
71 GLM-Image 1,012 Oct 2026 Official leaderboard
72 Gemini 2.0 Flash Preview Image Generation 976 Oct 2026 Official leaderboard
73 FLUX.1 [dev] 969 fp8 Oct 2026 Official leaderboard
74 DALL-E 3 967 Oct 2026 Official leaderboard
75 FLUX.1 Kontext [dev] 942 Oct 2026 Official leaderboard
76 Stable Diffusion 3.5 Large 938 Oct 2026 Official leaderboard
77 BAGEL 897 Oct 2026 Official leaderboard

3 models have held number one since its release in Dec 2024

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

Qwen xAI OpenAI
Own leaderboard 3 leaders

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%