Benchmark Almanac

Vision Arena

Claude Fable 5 1,309 leads since Jun 2026 Not in model cards

People send an image with a prompt, compare answers from two anonymous vision-language models, and vote for the better one. Votes become Bradley-Terry ratings.

Launched as the Multimodal Arena on 2024-06-27 with 17,429 votes. Since September 2025 an LLM filter drops image-generation prompts.

Made by Arena (formerly LMArena) Released Jun 2024 General visual questions 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 lmsys.org
153
Entries on its own leaderboard, 136 models we track

Claude Fable 5 leads with 1,309

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. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

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

  1. 1,309 Claude Fable 5
  2. 1,300 Qwen 3.8 Max
  3. 1,299 Claude Opus 4.6
  4. 1,299 Claude Opus 4.7
  5. 1,295 Gemini 3.7 Flash
  6. 1,294 Muse Spark
  7. 1,294 GPT-6.1 Sol
  8. 1,293 Claude Opus 5.5
  9. 1,293 Muse Spark 1.2
  10. 1,291 Gemini 3.8 Flash
  11. 1,290 Muse Spark 1.3
  12. 1,289 Gemini 3 Pro
  13. 1,288 Claude Opus 5
  14. 1,288 Claude Fable 5.1
  15. 1,286 GPT-5.6 Sol
  16. 1,286 GPT-5.5
  17. 1,286 Claude Opus 4.8
  18. 1,285 GPT-6 Astra
  19. 1,284 GPT-5.4
  20. 1,282 Gemini 3.5 Flash
  21. 1,282 Gemini 3.6 Flash
  22. 1,280 Muse Spark 1.1
  23. 1,280 Gemini 3.1 Pro
  24. 1,279 Grok 4.5
  25. 1,278 GPT-5.2 Instant
  26. 1,276 GPT-5.5 Instant
  27. 1,275 Claude Sonnet 4.6
  28. 1,273 Gemini 3 Flash
  29. 1,271 GLM-5.3-Flash
  30. 1,268 GPT-5.6 Terra
  31. 1,267 Gemini 3.5 Flash-Lite
  32. 1,266 GPT-6 Sol
  33. 1,265 Claude Sonnet 5.5
  34. 1,265 Kimi K2.6
  35. 1,263 Qwen3.7-Plus
  36. 1,262 Grok 4.6
  37. 1,262 Claude Sonnet 5
  38. 1,262 Gemma 4 31B IT
  39. 1,261 DeepSeek V4.1 Flash
  40. 1,257 GPT-5.6 Luna
  41. 1,256 Seed2.0 Pro
  42. 1,255 Grok 4.20 Beta (Reasoning, 0309)
  43. 1,252 Kimi K2.5
  44. 1,252 Mistral Large 4
  45. 1,251 GPT-5.1
  46. 1,250 GPT-5.4 Mini
  47. 1,250 Grok 4.20 Multi-Agent Beta (0309)
  48. 1,250 Grok 4.7
  49. 1,248 Gemini 2.5 Pro
  50. 1,247 Step 5 Preview
  51. 1,246 Qwen3.5 397B-A17B
  52. 1,245 MiMo-V2.6 Pro
  53. 1,245 MiMo-V2.6 Flash
  54. 1,243 GPT-5.2
  55. 1,242 Qwen 3.8 27B
  56. 1,242 Grok 4.3
  57. 1,242 Gemma 4 26B A4B
  58. 1,240 GPT-6 Luna
  59. 1,239 GPT-4o
  60. 1,235 Gemini 3.1 Flash-Lite
  61. 1,234 MiMo-V2.5
  62. 1,233 MiniMax-M3
  63. 1,230 GLM-5V-Turbo
  64. 1,230 Gemini 2.5 Flash
  65. 1,226 Qwen3.5-122B-A10B
  66. 1,226 GPT-5 Chat
  67. 1,225 GPT-4.5
  68. 1,219 ERNIE-5.0-Preview (1220)
  69. 1,217 Qwen3.5-27B
  70. 1,216 MiMo-V2-Omni
  71. 1,216 o3
  72. 1,215 Gemini 2.5 Flash
  73. 1,215 Qwen3-VL-235B-A22B-Instruct
  74. 1,214 GPT-4.1
  75. 1,211 GPT-5
  76. 1,209 Inkling-Small
  77. 1,208 Claude Opus 4
  78. 1,207 Claude Sonnet 4
  79. 1,204 Nemotron 3.5 Super VL
  80. 1,201 o4-mini
  81. 1,201 GPT-4.1 mini
  82. 1,200 Mistral Medium 3.5
  83. 1,199 Mistral Large 3
  84. 1,199 GPT-5.4 Nano
  85. 1,196 Grok 4.1 Fast
  86. 1,193 o1
  87. 1,193 Claude 3.7 Sonnet
  88. 1,189 Qwen3-VL-235B-A22B
  89. 1,189 Gemini 2.5 Flash-Lite
  90. 1,185 Qwen-VL-Max
  91. 1,184 GPT-5 mini
  92. 1,184 Grok 4
  93. 1,179 Gemini 1.5 Pro
  94. 1,175 Gemini 2.5 Flash-Lite
  95. 1,172 Gemini 2.0 Flash
  96. 1,162 GPT-4o
  97. 1,161 GLM-4.6V
  98. 1,161 Claude 3.5 Sonnet (October 2024)
  99. 1,160 Gemma 3 27B
  100. 1,160 Mistral Medium 3.1
  101. 1,156 Step-1o Turbo (202506)
  102. 1,155 Mistral Medium 3
  103. 1,155 Hunyuan Vision 1.5 Thinking
  104. 1,153 GLM-4.5V
  105. 1,150 Hunyuan Large Vision
  106. 1,147 GPT-5 nano
  107. 1,145 Llama 4 Maverick
  108. 1,145 Claude 3.5 Sonnet
  109. 1,145 Step 3
  110. 1,142 Gemini 1.5 Flash
  111. 1,140 Mistral Small 3.2
  112. 1,136 Gemini 2.0 Flash-Lite
  113. 1,128 Llama 4 Scout
  114. 1,127 Claude 3.5 Haiku
  115. 1,127 Mistral Small 3.1
  116. 1,124 Step-1o Vision 32K (High Res)
  117. 1,121 Qwen2.5-VL-72B
  118. 1,120 Gemini 1.5 Pro
  119. 1,119 Qwen2.5-VL-32B
  120. 1,118 GPT-4o
  121. 1,112 Molmo2-8B
  122. 1,112 GPT-4 Turbo
  123. 1,097 GPT-4o mini
  124. 1,095 Pixtral Large (2411)
  125. 1,089 GPT-4.1 nano
  126. 1,085 Qwen2-VL-72B
  127. 1,085 Qwen-VL-Max (1119)
  128. 1,071 Gemini 1.5 Flash 8B
  129. 1,064 Step-1V 32K
  130. 1,062 Claude 3 Opus
  131. 1,059 Gemini 1.5 Flash
  132. 1,045 Molmo-72B
  133. 1,042 Hunyuan Standard Vision 20241231
  134. 1,032 Llama 3.2 90B
  135. 1,031 Qwen2-VL-7B-Instruct
  136. 1,025 Pixtral 12B (2409)
  137. 1,025 InternVL2-26B
  138. 1,019 Amazon Nova Lite
  139. 1,018 Amazon Nova Pro
  140. 1,016 Claude 3 Sonnet
  141. 1,002 Yi Vision
  142. 1,000 Aya Vision 32B
  143. 1,000 Claude 3 Haiku
  144. 994 Molmo-7B-D
  145. 993 Llama 3.2 11B
  146. 985 nvila-internal-15b-v1
  147. 978 LLaVA-OneVision Qwen2 72B OV
  148. 964 LLaVA 1.6 34B
  149. 964 CogVLM2-19B-Chat
  150. 962 MiniCPM-V-2_6
  151. 958 InternVL2-4B
  152. 919 Phi-3.5-vision-instruct
  153. 881 Phi-3-vision-128k-instruct

Bars start at 800.

  1. 1 Claude Fable 5 high 1,309
  2. 2 Qwen 3.8 Max 1,300
  3. 3 Claude Opus 4.6 high 1,299
  4. 4 Claude Opus 4.7 1,299
  5. 5 Gemini 3.7 Flash high 1,295
  6. 6 Muse Spark 1,294
  7. 7 GPT-6.1 Sol max 1,294
  8. 8 Claude Opus 5.5 high 1,293
  9. 9 Muse Spark 1.2 xhigh 1,293
  10. 10 Gemini 3.8 Flash high 1,291
  11. 11 Muse Spark 1.3 max 1,290
  12. 12 Gemini 3 Pro 1,289
  13. 13 Claude Opus 5 high 1,288
  14. 14 Claude Fable 5.1 max 1,288
  15. 15 GPT-5.6 Sol xhigh 1,286
  16. 16 GPT-5.5 1,286
  17. 17 Claude Opus 4.8 high 1,286
  18. 18 GPT-6 Astra max 1,285
  19. 19 GPT-5.4 high 1,284
  20. 20 Gemini 3.5 Flash medium 1,282
  21. 21 Gemini 3.6 Flash high 1,282
  22. 22 Muse Spark 1.1 1,280
  23. 23 Gemini 3.1 Pro 1,280
  24. 24 Grok 4.5 1,279
  25. 25 GPT-5.2 Instant 1,278
  26. 26 GPT-5.5 Instant 1,276
  27. 27 Claude Sonnet 4.6 1,275
  28. 28 Gemini 3 Flash 1,273
  29. 29 GLM-5.3-Flash 1,271
  30. 30 GPT-5.6 Terra xhigh 1,268
  31. 31 Gemini 3.5 Flash-Lite 1,267
  32. 32 GPT-6 Sol max 1,266
  33. 33 Claude Sonnet 5.5 xhigh 1,265
  34. 34 Kimi K2.6 1,265
  35. 35 Qwen3.7-Plus 1,263
  36. 36 Grok 4.6 high 1,262
  37. 37 Claude Sonnet 5 high 1,262
  38. 38 Gemma 4 31B IT 1,262
  39. 39 DeepSeek V4.1 Flash max 1,261
  40. 40 GPT-5.6 Luna xhigh 1,257
  41. 41 Seed2.0 Pro 1,256
  42. 42 Grok 4.20 Beta (Reasoning, 0309) 1,255
  43. 43 Kimi K2.5 thinking 1,252
  44. 44 Mistral Large 4 1,252
  45. 45 GPT-5.1 high 1,251
  46. 46 GPT-5.4 Mini high 1,250
  47. 47 Grok 4.20 Multi-Agent Beta (0309) 1,250
  48. 48 Grok 4.7 xhigh 1,250
  49. 49 Gemini 2.5 Pro Jun 2025 1,248
  50. 50 Step 5 Preview 1,247
  51. 51 Qwen3.5 397B-A17B 1,246
  52. 52 MiMo-V2.6 Pro 1,245
  53. 53 MiMo-V2.6 Flash 1,245
  54. 54 GPT-5.2 high 1,243
  55. 55 Qwen 3.8 27B 1,242
  56. 56 Grok 4.3 1,242
  57. 57 Gemma 4 26B A4B 1,242
  58. 58 GPT-6 Luna max 1,240
  59. 59 GPT-4o Mar 2025 1,239
  60. 60 Gemini 3.1 Flash-Lite 1,235
  61. 61 MiMo-V2.5 1,234
  62. 62 MiniMax-M3 1,233
  63. 63 GLM-5V-Turbo 1,230
  64. 64 Gemini 2.5 Flash Sep 2025 1,230
  65. 65 Qwen3.5-122B-A10B 1,226
  66. 66 GPT-5 Chat 1,226
  67. 67 GPT-4.5 1,225
  68. 68 ERNIE-5.0-Preview (1220) 1,219
  69. 69 Qwen3.5-27B 1,217
  70. 70 MiMo-V2-Omni 1,216
  71. 71 o3 1,216
  72. 72 Gemini 2.5 Flash Jun 2025 1,215
  73. 73 Qwen3-VL-235B-A22B-Instruct 1,215
  74. 74 GPT-4.1 1,214
  75. 75 GPT-5 high 1,211
  76. 76 Inkling-Small 1,209
  77. 77 Claude Opus 4 thinking 16k 1,208
  78. 78 Claude Sonnet 4 thinking 32k 1,207
  79. 79 Nemotron 3.5 Super VL nvfp4 1,204
  80. 80 o4-mini 1,201
  81. 81 GPT-4.1 mini 1,201
  82. 82 Mistral Medium 3.5 1,200
  83. 83 Mistral Large 3 1,199
  84. 84 GPT-5.4 Nano high 1,199
  85. 85 Grok 4.1 Fast reasoning 1,196
  86. 86 o1 1,193
  87. 87 Claude 3.7 Sonnet thinking 32k 1,193
  88. 88 Qwen3-VL-235B-A22B thinking 1,189
  89. 89 Gemini 2.5 Flash-Lite Jun 2025 1,189
  90. 90 Qwen-VL-Max 1,185
  91. 91 GPT-5 mini high 1,184
  92. 92 Grok 4 1,184
  93. 93 Gemini 1.5 Pro Sep 2024 1,179
  94. 94 Gemini 2.5 Flash-Lite Sep 2025, non-thinking, 09-2025 1,175
  95. 95 Gemini 2.0 Flash Feb 2025 1,172
  96. 96 GPT-4o May 2024 1,162
  97. 97 GLM-4.6V 1,161
  98. 98 Claude 3.5 Sonnet (October 2024) 1,161
  99. 99 Gemma 3 27B 1,160
  100. 100 Mistral Medium 3.1 1,160
  101. 101 Step-1o Turbo (202506) 1,156
  102. 102 Mistral Medium 3 1,155
  103. 103 Hunyuan Vision 1.5 Thinking 1,155
  104. 104 GLM-4.5V 1,153
  105. 105 Hunyuan Large Vision 1,150
  106. 106 GPT-5 nano high 1,147
  107. 107 Llama 4 Maverick 1,145
  108. 108 Claude 3.5 Sonnet 1,145
  109. 109 Step 3 1,145
  110. 110 Gemini 1.5 Flash Sep 2024 1,142
  111. 111 Mistral Small 3.2 1,140
  112. 112 Gemini 2.0 Flash-Lite 1,136
  113. 113 Llama 4 Scout 1,128
  114. 114 Claude 3.5 Haiku 1,127
  115. 115 Mistral Small 3.1 1,127
  116. 116 Step-1o Vision 32K (High Res) 1,124
  117. 117 Qwen2.5-VL-72B 1,121
  118. 118 Gemini 1.5 Pro May 2024 1,120
  119. 119 Qwen2.5-VL-32B 1,119
  120. 120 GPT-4o Aug 2024 1,118
  121. 121 Molmo2-8B 1,112
  122. 122 GPT-4 Turbo Apr 2024 1,112
  123. 123 GPT-4o mini 1,097
  124. 124 Pixtral Large (2411) 1,095
  125. 125 GPT-4.1 nano 1,089
  126. 126 Qwen2-VL-72B 1,085
  127. 127 Qwen-VL-Max (1119) 1,085
  128. 128 Gemini 1.5 Flash 8B 1,071
  129. 129 Step-1V 32K 1,064
  130. 130 Claude 3 Opus 1,062
  131. 131 Gemini 1.5 Flash May 2024 1,059
  132. 132 Molmo-72B 1,045
  133. 133 Hunyuan Standard Vision 20241231 1,042
  134. 134 Llama 3.2 90B 1,032
  135. 135 Qwen2-VL-7B-Instruct 1,031
  136. 136 Pixtral 12B (2409) 1,025
  137. 137 InternVL2-26B 1,025
  138. 138 Amazon Nova Lite 1,019
  139. 139 Amazon Nova Pro 1,018
  140. 140 Claude 3 Sonnet 1,016
  141. 141 Yi Vision 1,002
  142. 142 Aya Vision 32B 1,000
  143. 143 Claude 3 Haiku 1,000
  144. 144 Molmo-7B-D 994
  145. 145 Llama 3.2 11B 993
  146. 146 nvila-internal-15b-v1 985
  147. 147 LLaVA-OneVision Qwen2 72B OV 978
  148. 148 LLaVA 1.6 34B 964
  149. 149 CogVLM2-19B-Chat 964
  150. 150 MiniCPM-V-2_6 962
  151. 151 InternVL2-4B 958
  152. 152 Phi-3.5-vision-instruct 919
  153. 153 Phi-3-vision-128k-instruct 881
#EntryScoreSettingDateSource
1 Claude Fable 5 1,309 high Jun 2026 Official leaderboard
2 Qwen 3.8 Max 1,300 Aug 2026 Official leaderboard
3 Claude Opus 4.6 1,299 high Feb 2026 Official leaderboard
4 Claude Opus 4.7 1,299 Apr 2026 Official leaderboard
5 Gemini 3.7 Flash 1,295 high Aug 2026 Official leaderboard
6 Muse Spark 1,294 Apr 2026 Official leaderboard
7 GPT-6.1 Sol 1,294 max Sep 2026 Official leaderboard
8 Claude Opus 5.5 1,293 high Sep 2026 Official leaderboard
9 Muse Spark 1.2 1,293 xhigh Aug 2026 Official leaderboard
10 Gemini 3.8 Flash 1,291 high Sep 2026 Official leaderboard
11 Muse Spark 1.3 1,290 max Sep 2026 Official leaderboard
12 Gemini 3 Pro 1,289 Nov 2025 Official leaderboard
13 Claude Opus 5 1,288 high Jul 2026 Official leaderboard
14 Claude Fable 5.1 1,288 max Sep 2026 Official leaderboard
15 GPT-5.6 Sol 1,286 xhigh Jul 2026 Official leaderboard
16 GPT-5.5 1,286 Apr 2026 Official leaderboard
17 Claude Opus 4.8 1,286 high May 2026 Official leaderboard
18 GPT-6 Astra 1,285 max Sep 2026 Official leaderboard
19 GPT-5.4 1,284 high Mar 2026 Official leaderboard
20 Gemini 3.5 Flash 1,282 medium May 2026 Official leaderboard
21 Gemini 3.6 Flash 1,282 high Jul 2026 Official leaderboard
22 Muse Spark 1.1 1,280 Jul 2026 Official leaderboard
23 Gemini 3.1 Pro 1,280 Feb 2026 Official leaderboard
24 Grok 4.5 1,279 Jul 2026 Official leaderboard
25 GPT-5.2 Instant 1,278 Dec 2025 Official leaderboard
26 GPT-5.5 Instant 1,276 May 2026 Official leaderboard
27 Claude Sonnet 4.6 1,275 Feb 2026 Official leaderboard
28 Gemini 3 Flash 1,273 Dec 2025 Official leaderboard
29 GLM-5.3-Flash 1,271 Aug 2026 Official leaderboard
30 GPT-5.6 Terra 1,268 xhigh Jul 2026 Official leaderboard
31 Gemini 3.5 Flash-Lite 1,267 Jul 2026 Official leaderboard
32 GPT-6 Sol 1,266 max Sep 2026 Official leaderboard
33 Claude Sonnet 5.5 1,265 xhigh Sep 2026 Official leaderboard
34 Kimi K2.6 1,265 Apr 2026 Official leaderboard
35 Qwen3.7-Plus 1,263 Jun 2026 Official leaderboard
36 Grok 4.6 1,262 high Aug 2026 Official leaderboard
37 Claude Sonnet 5 1,262 high Jun 2026 Official leaderboard
38 Gemma 4 31B IT 1,262 Apr 2026 Official leaderboard
39 DeepSeek V4.1 Flash 1,261 max Sep 2026 Official leaderboard
40 GPT-5.6 Luna 1,257 xhigh Jul 2026 Official leaderboard
41 Seed2.0 Pro 1,256 Feb 2026 Official leaderboard
42 Grok 4.20 Beta (Reasoning, 0309) 1,255 Oct 2026 Official leaderboard
43 Kimi K2.5 1,252 thinking Jan 2026 Official leaderboard
44 Mistral Large 4 1,252 Oct 2026 Official leaderboard
45 GPT-5.1 1,251 high Nov 2025 Official leaderboard
46 GPT-5.4 Mini 1,250 high Mar 2026 Official leaderboard
47 Grok 4.20 Multi-Agent Beta (0309) 1,250 Oct 2026 Official leaderboard
48 Grok 4.7 1,250 xhigh Sep 2026 Official leaderboard
49 Gemini 2.5 Pro Jun 2025 1,248 Jun 2025 Official leaderboard
50 Step 5 Preview 1,247 Sep 2026 Official leaderboard
51 Qwen3.5 397B-A17B 1,246 Feb 2026 Official leaderboard
52 MiMo-V2.6 Pro 1,245 Sep 2026 Official leaderboard
53 MiMo-V2.6 Flash 1,245 Sep 2026 Official leaderboard
54 GPT-5.2 1,243 high Dec 2025 Official leaderboard
55 Qwen 3.8 27B 1,242 Aug 2026 Official leaderboard
56 Grok 4.3 1,242 Apr 2026 Official leaderboard
57 Gemma 4 26B A4B 1,242 Apr 2026 Official leaderboard
58 GPT-6 Luna 1,240 max Sep 2026 Official leaderboard
59 GPT-4o Mar 2025 1,239 Mar 2025 Official leaderboard
60 Gemini 3.1 Flash-Lite 1,235 Mar 2026 Official leaderboard
61 MiMo-V2.5 1,234 Apr 2026 Official leaderboard
62 MiniMax-M3 1,233 Jun 2026 Official leaderboard
63 GLM-5V-Turbo 1,230 Apr 2026 Official leaderboard
64 Gemini 2.5 Flash Sep 2025 1,230 Sep 2025 Official leaderboard
65 Qwen3.5-122B-A10B 1,226 Feb 2026 Official leaderboard
66 GPT-5 Chat 1,226 Aug 2025 Official leaderboard
67 GPT-4.5 1,225 Feb 2025 Official leaderboard
68 ERNIE-5.0-Preview (1220) 1,219 Oct 2026 Official leaderboard
69 Qwen3.5-27B 1,217 Feb 2026 Official leaderboard
70 MiMo-V2-Omni 1,216 Mar 2026 Official leaderboard
71 o3 1,216 Apr 2025 Official leaderboard
72 Gemini 2.5 Flash Jun 2025 1,215 Jun 2025 Official leaderboard
73 Qwen3-VL-235B-A22B-Instruct 1,215 Sep 2025 Official leaderboard
74 GPT-4.1 1,214 Apr 2025 Official leaderboard
75 GPT-5 1,211 high Aug 2025 Official leaderboard
76 Inkling-Small 1,209 Jul 2026 Official leaderboard
77 Claude Opus 4 1,208 thinking 16k May 2025 Official leaderboard
78 Claude Sonnet 4 1,207 thinking 32k May 2025 Official leaderboard
79 Nemotron 3.5 Super VL 1,204 nvfp4 Oct 2026 Official leaderboard
80 o4-mini 1,201 Apr 2025 Official leaderboard
81 GPT-4.1 mini 1,201 Apr 2025 Official leaderboard
82 Mistral Medium 3.5 1,200 Apr 2026 Official leaderboard
83 Mistral Large 3 1,199 Dec 2025 Official leaderboard
84 GPT-5.4 Nano 1,199 high Mar 2026 Official leaderboard
85 Grok 4.1 Fast 1,196 reasoning Nov 2025 Official leaderboard
86 o1 1,193 Dec 2024 Official leaderboard
87 Claude 3.7 Sonnet 1,193 thinking 32k Feb 2025 Official leaderboard
88 Qwen3-VL-235B-A22B 1,189 thinking Sep 2025 Official leaderboard
89 Gemini 2.5 Flash-Lite Jun 2025 1,189 Jun 2025 Official leaderboard
90 Qwen-VL-Max 1,185 Jan 2024 Official leaderboard
91 GPT-5 mini 1,184 high Aug 2025 Official leaderboard
92 Grok 4 1,184 Jul 2025 Official leaderboard
93 Gemini 1.5 Pro Sep 2024 1,179 Sep 2024 Official leaderboard
94 Gemini 2.5 Flash-Lite Sep 2025 1,175 non-thinking, 09-2025 Sep 2025 Official leaderboard
95 Gemini 2.0 Flash Feb 2025 1,172 Feb 2025 Official leaderboard
96 GPT-4o May 2024 1,162 May 2024 Official leaderboard
97 GLM-4.6V 1,161 Dec 2025 Official leaderboard
98 Claude 3.5 Sonnet (October 2024) 1,161 Oct 2024 Official leaderboard
99 Gemma 3 27B 1,160 Mar 2025 Official leaderboard
100 Mistral Medium 3.1 1,160 Aug 2025 Official leaderboard
101 Step-1o Turbo (202506) 1,156 Oct 2026 Official leaderboard
102 Mistral Medium 3 1,155 May 2025 Official leaderboard
103 Hunyuan Vision 1.5 Thinking 1,155 Oct 2026 Official leaderboard
104 GLM-4.5V 1,153 Aug 2025 Official leaderboard
105 Hunyuan Large Vision 1,150 Oct 2026 Official leaderboard
106 GPT-5 nano 1,147 high Aug 2025 Official leaderboard
107 Llama 4 Maverick 1,145 Apr 2025 Official leaderboard
108 Claude 3.5 Sonnet 1,145 Jun 2024 Official leaderboard
109 Step 3 1,145 Jul 2025 Official leaderboard
110 Gemini 1.5 Flash Sep 2024 1,142 Aug 2024 Official leaderboard
111 Mistral Small 3.2 1,140 Jun 2025 Official leaderboard
112 Gemini 2.0 Flash-Lite 1,136 Feb 2025 Official leaderboard
113 Llama 4 Scout 1,128 Apr 2025 Official leaderboard
114 Claude 3.5 Haiku 1,127 Oct 2024 Official leaderboard
115 Mistral Small 3.1 1,127 Mar 2025 Official leaderboard
116 Step-1o Vision 32K (High Res) 1,124 Oct 2026 Official leaderboard
117 Qwen2.5-VL-72B 1,121 Jan 2025 Official leaderboard
118 Gemini 1.5 Pro May 2024 1,120 May 2024 Official leaderboard
119 Qwen2.5-VL-32B 1,119 Mar 2025 Official leaderboard
120 GPT-4o Aug 2024 1,118 Aug 2024 Official leaderboard
121 Molmo2-8B 1,112 Dec 2025 Official leaderboard
122 GPT-4 Turbo Apr 2024 1,112 Apr 2024 Official leaderboard
123 GPT-4o mini 1,097 Jul 2024 Official leaderboard
124 Pixtral Large (2411) 1,095 Oct 2026 Official leaderboard
125 GPT-4.1 nano 1,089 Apr 2025 Official leaderboard
126 Qwen2-VL-72B 1,085 Oct 2026 Official leaderboard
127 Qwen-VL-Max (1119) 1,085 Oct 2026 Official leaderboard
128 Gemini 1.5 Flash 8B 1,071 Oct 2024 Official leaderboard
129 Step-1V 32K 1,064 Oct 2026 Official leaderboard
130 Claude 3 Opus 1,062 Feb 2024 Official leaderboard
131 Gemini 1.5 Flash May 2024 1,059 May 2024 Official leaderboard
132 Molmo-72B 1,045 Sep 2024 Official leaderboard
133 Hunyuan Standard Vision 20241231 1,042 Dec 2024 Official leaderboard
134 Llama 3.2 90B 1,032 Sep 2024 Official leaderboard
135 Qwen2-VL-7B-Instruct 1,031 Aug 2024 Official leaderboard
136 Pixtral 12B (2409) 1,025 Oct 2026 Official leaderboard
137 InternVL2-26B 1,025 Jul 2024 Official leaderboard
138 Amazon Nova Lite 1,019 Dec 2024 Official leaderboard
139 Amazon Nova Pro 1,018 Dec 2024 Official leaderboard
140 Claude 3 Sonnet 1,016 Feb 2024 Official leaderboard
141 Yi Vision 1,002 Oct 2026 Official leaderboard
142 Aya Vision 32B 1,000 Mar 2025 Official leaderboard
143 Claude 3 Haiku 1,000 Mar 2024 Official leaderboard
144 Molmo-7B-D 994 Sep 2024 Official leaderboard
145 Llama 3.2 11B 993 Sep 2024 Official leaderboard
146 nvila-internal-15b-v1 985 Oct 2026 Official leaderboard
147 LLaVA-OneVision Qwen2 72B OV 978 Oct 2026 Official leaderboard
148 LLaVA 1.6 34B 964 Oct 2026 Official leaderboard
149 CogVLM2-19B-Chat 964 May 2024 Official leaderboard
150 MiniCPM-V-2_6 962 Aug 2024 Official leaderboard
151 InternVL2-4B 958 Jul 2024 Official leaderboard
152 Phi-3.5-vision-instruct 919 Aug 2024 Official leaderboard
153 Phi-3-vision-128k-instruct 881 May 2024 Official leaderboard

More effort adds a median 2 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 4.6
high
1,299
Claude Opus 4.7
high
1,299
Muse Spark 1.3
xhigh
1,290
GPT-5.5
high
1,286
Claude Opus 4.8
high
1,286
GPT-5.4
high
1,284
Gemini 3.5 Flash
medium
1,282
Gemini 3 Flash
minimal
1,273
Kimi K2.5
instant thinking
1,252
GPT-5.1
high
1,251
GPT-5.2
high
1,243
Claude Opus 4
thinking 16k
1,208
ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5 high 1,309
Qwen 3.8 Max 1,300
Claude Opus 4.6 high 1,299
Claude Opus 4.7 1,299
Claude Opus 4.7 high 1,298
Gemini 3.7 Flash high 1,295
Muse Spark 1,294
Claude Opus 4.6 1,294
GPT-6.1 Sol max 1,294
Claude Opus 5.5 high 1,293
Muse Spark 1.2 xhigh 1,293
Gemini 3.8 Flash high 1,291
Muse Spark 1.3 max 1,290
Gemini 3 Pro 1,289
Claude Opus 5 high 1,288
Muse Spark 1.3 xhigh 1,288
Claude Fable 5.1 max 1,288
GPT-5.6 Sol xhigh 1,286
GPT-5.5 1,286
Claude Opus 4.8 high 1,286
GPT-6 Astra max 1,285
GPT-5.4 high 1,284
Gemini 3.5 Flash medium 1,282
Gemini 3.5 Flash high 1,282
GPT-5.5 high 1,282
Gemini 3.6 Flash high 1,282
Muse Spark 1.1 1,280
Gemini 3.1 Pro 1,280
Grok 4.5 1,279
Claude Opus 4.8 1,279
GPT-5.4 1,279
GPT-5.2 Instant 1,278
GPT-5.5 Instant 1,276
Claude Sonnet 4.6 1,275
Gemini 3 Flash 1,273
GLM-5.3-Flash 1,271
GPT-5.6 Terra xhigh 1,268
Gemini 3.5 Flash-Lite 1,267
GPT-6 Sol max 1,266
Claude Sonnet 5.5 xhigh 1,265
Kimi K2.6 1,265
Qwen3.7-Plus 1,263
Grok 4.6 high 1,262
Claude Sonnet 5 high 1,262
Gemma 4 31B IT 1,262
DeepSeek V4.1 Flash max 1,261
Gemini 3 Flash minimal 1,260
GPT-5.6 Luna xhigh 1,257
Seed2.0 Pro 1,256
Kimi K2.5 thinking 1,252
Mistral Large 4 1,252
GPT-5.1 high 1,251
GPT-5.4 Mini high 1,250
Grok 4.7 xhigh 1,250
Gemini 2.5 Pro Jun 2025 1,248
Step 5 Preview 1,247
Qwen3.5 397B-A17B 1,246
MiMo-V2.6 Pro 1,245
MiMo-V2.6 Flash 1,245
GPT-5.2 high 1,243
Qwen 3.8 27B 1,242
Grok 4.3 1,242
Gemma 4 26B A4B 1,242
GPT-6 Luna max 1,240
GPT-5.1 1,240
GPT-4o Mar 2025 1,239
Kimi K2.5 instant 1,236
Gemini 3.1 Flash-Lite 1,235
MiMo-V2.5 1,234
MiniMax-M3 1,233
GLM-5V-Turbo 1,230
Gemini 2.5 Flash Sep 2025 1,230
GPT-5.2 1,228
Qwen3.5-122B-A10B 1,226
GPT-5 Chat 1,226
GPT-4.5 1,225
Qwen3.5-27B 1,217
MiMo-V2-Omni 1,216
o3 1,216
Gemini 2.5 Flash Jun 2025 1,215
Qwen3-VL-235B-A22B-Instruct 1,215
GPT-4.1 1,214
GPT-5 high 1,211
Inkling-Small 1,209
Claude Opus 4 thinking 16k 1,208
Claude Sonnet 4 thinking 32k 1,207
Nemotron 3.5 Super VL nvfp4 1,204
o4-mini 1,201
GPT-4.1 mini 1,201
Mistral Medium 3.5 1,200
Mistral Large 3 1,199
GPT-5.4 Nano high 1,199
Grok 4.1 Fast reasoning 1,196
o1 1,193
Claude 3.7 Sonnet thinking 32k 1,193
Claude Opus 4 1,189
Qwen3-VL-235B-A22B thinking 1,189
Gemini 2.5 Flash-Lite Jun 2025 1,189
Claude Sonnet 4 1,189
Qwen-VL-Max 1,185
GPT-5 mini high 1,184
Grok 4 1,184
Gemini 1.5 Pro Sep 2024 1,179
Claude 3.7 Sonnet 1,175
Gemini 2.5 Flash-Lite Sep 2025 non-thinking, 09-2025 1,175
Gemini 2.0 Flash Feb 2025 1,172
GPT-4o May 2024 1,162
GLM-4.6V 1,161
Claude 3.5 Sonnet (October 2024) 1,161
Gemma 3 27B 1,160
Mistral Medium 3.1 1,160
Mistral Medium 3 1,155
GLM-4.5V 1,153
GPT-5 nano high 1,147
Llama 4 Maverick 1,145
Claude 3.5 Sonnet 1,145
Step 3 1,145
Gemini 1.5 Flash Sep 2024 1,142
Mistral Small 3.2 1,140
Gemini 2.0 Flash-Lite 1,136
Llama 4 Scout 1,128
Claude 3.5 Haiku 1,127
Mistral Small 3.1 1,127
Qwen2.5-VL-72B 1,121
Gemini 1.5 Pro May 2024 1,120
Qwen2.5-VL-32B 1,119
GPT-4o Aug 2024 1,118
Molmo2-8B 1,112
GPT-4 Turbo Apr 2024 1,112
GPT-4o mini 1,097
GPT-4.1 nano 1,089
Gemini 1.5 Flash 8B 1,071
Claude 3 Opus 1,062
Gemini 1.5 Flash May 2024 1,059
Molmo-72B 1,045
Llama 3.2 90B 1,032
Qwen2-VL-7B-Instruct 1,031
InternVL2-26B 1,025
Amazon Nova Lite 1,019
Amazon Nova Pro 1,018
Claude 3 Sonnet 1,016
Aya Vision 32B 1,000
Claude 3 Haiku 1,000
Molmo-7B-D 994
Llama 3.2 11B 993
CogVLM2-19B-Chat 964
MiniCPM-V-2_6 962
InternVL2-4B 958
Phi-3.5-vision-instruct 919
Phi-3-vision-128k-instruct 881

9 models have held number one since its release in Jun 2024

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

Other labs OpenAI Google DeepMind Anthropic
Own leaderboard 9 leaders
Claude Fable 5 1,309

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 2024 2025 2026 800 1,000 1,200 1,400 2024 2025 2026

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%