Design Arena: all code categories leaderboard
- models measured
- 126
- lead over #2
- +11 Elo
- median
- 1206
Leader on Design Arena: all code categories · read October 21
On October 21, 2026, 126 of our catalog's models had a Design Arena: all code categories result, and Anthropic Claude Opus 5.5 led with 1390.
Design Arena shows people two designs made by two models from the same prompt (any of its code categories) and asks which is better. The number is the Elo rating built from those votes, as Design Arena publishes it.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Battles | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5Anthropic | 1390 | 4,597 | 92.2 | $20.00 | |
| 2 | GPT-6 AstraOpenAI | 1379 | 8,887 | 88.7 | $50.00 | |
| 3 | Muse WonderMeta | 1370 | 5,648 | 64.5 | $20.00 | |
| 4 | Claude Sonnet 5.5Anthropic | 1364 | 2,952 | 88.9 | $10.00 | |
| 5 | Kimi K3Moonshot AI | 1361 | 8,988 | 61.8 | $11.936 | |
| 6 | Muse Spark 1.3Meta | 1353 | 44,509 | 79.7 | $4.25 | |
| 7 | GPT-6.1 SolOpenAI | 1345 | 3,275 | 88.7 | $10.00 | |
| 8 | GPT-5.6 SolOpenAI | 1341 | 13,470 | 76.7 | $20.00 | |
| 9 | Claude Fable 5.1Anthropic | 1336 | 9,349 | 89.1 | $50.00 | |
| 10 | DeepSeek V4.1 Flash 1017DeepSeek | 1335 | 2,443 | 83.3 | $0.60 | |
| 11 | Gemini 4 ArgonGoogle | 1328 | 10,385 | 80.5 | $10.00 | |
| 12 | Claude Opus 5Anthropic | 1324 | 19,251 | 81.8 | $25.00 | |
| 13 | DeepSeek V4.1 FlashDeepSeek | 1320 | 42,167 | 77.2 | $0.525 | |
| 14 | MiMo-V2.6-ProXiaomi | 1317 | Not published | 72.6 | $0.87 | |
| 15 | Muse Spark 1.2Meta | 1313 | 50,357 | 65.1 | $4.25 | |
| 16 | Claude Fable 5Anthropic | 1310 | 20,216 | 82.1 | $50.00 | |
| 17 | Gemini 3.7 FlashGoogle | 1308 | 77,434 | 69.9 | $3.75 | |
| 18 | Gemini 3.8 FlashGoogle | 1304 | 45,973 | 70.5 | $4.125 | |
| 19 | GLM 5.3Z.ai | 1304 | Not published | 73.1 | $1.40 | |
| 20 | GPT-6 SolOpenAI | 1301 | 5,449 | 82.8 | $10.00 | |
| 21 | Qwen3.8 Max (0902)Qwen | 1293 | 11,210 | 63.5 | $6.00 | |
| 22 | Grok 4.6xAI | 1292 | Not published | 76.4 | $6.00 | |
| 23 | Gemini 3.6 FlashGoogle | 1290 | 32,658 | 48.3 | $3.75 | |
| 24 | Claude Opus 4.6Anthropic | 1289 | 27,406 | 66.9 | $25.00 | |
| 25 | GLM 5.2Z.ai | 1288 | 56,856 | 57.7 | $7.00 | |
| 26 | GLM 5.3 FlashZ.ai | 1282 | Not published | 71.0 | $0.50 | |
| 27 | Claude Haiku 5.5Anthropic | 1279 | 9,233 | 75.9 | $0.50 | |
| 28 | Claude Sonnet 4.6Anthropic | 1276 | 26,317 | 57.8 | $15.00 | |
| 29 | Claude Sonnet 5Anthropic | 1276 | 24,225 | 63.5 | $10.00 | |
| 30 | Muse Spark 1.1Meta | 1276 | Not published | 48.9 | $4.25 | |
| 31 | Grok 4.5xAI | 1276 | Not published | 75.5 | $6.00 | |
| 32 | Qwen3.7 MaxQwen | 1275 | 36,466 | 45.1 | $4.425 | |
| 33 | Kimi K2.6Moonshot AI | 1272 | 34,045 | 44.2 | $3.41 | |
| 34 | GPT-6 LunaOpenAI | 1271 | 7,151 | 71.4 | $0.50 | |
| 35 | Grok 4.7xAI | 1271 | 2,834 | 75.0 | $6.00 | |
| 36 | Qwen3.7 PlusQwen | 1269 | 18,698 | Not benchmarked | $1.28 | |
| 37 | GLM 5.1Z.ai | 1268 | Not published | 44.0 | $4.40 | |
| 38 | Gemini 3.5 FlashGoogle | 1266 | 36,918 | 42.8 | $9.00 | |
| 39 | MiMo-V2.5-ProXiaomi | 1266 | 28,661 | 40.0 | $0.609 | |
| 40 | GLM 5 TurboZ.ai | 1262 | 42,055 | Not benchmarked | $4.00 | |
| 41 | GPT-5.5OpenAI | 1260 | 33,866 | 67.8 | $30.00 | |
| 42 | MiMo-V2.5Xiaomi | 1260 | 44,768 | 34.0 | $0.238 | |
| 43 | Mistral Large 4Mistral AI | 1259 | 5,990 | 55.3 | $4.18 | |
| 44 | Claude Opus 4.8Anthropic | 1255 | 32,806 | 66.0 | $25.00 | |
| 45 | Kimi K2.7 CodeMoonshot AI | 1253 | 22,556 | 39.1 | $3.35 | |
| 46 | MiniMax M3MiniMax | 1247 | 27,590 | 57.8 | $1.20 | |
| 47 | GLM 5Z.ai | 1246 | 45,368 | 59.7 | $3.20 | |
| 48 | Claude Opus 4.5Anthropic | 1242 | 35,207 | 66.8 | $25.00 | |
| 49 | GPT-5.6 TerraOpenAI | 1241 | 74,711 | 69.0 | $12.00 | |
| 50 | DeepSeek V4 Pro 0423DeepSeek | 1240 | 27,276 | 35.3 | $1.9105 | |
| 51 | Kimi K2.5Moonshot AI | 1236 | 41,642 | 58.5 | $2.50 | |
| 52 | Qwen3.6 PlusQwen | 1236 | 39,209 | 37.4 | $1.95 | |
| 53 | Mercury 3Inception | 1234 | 1,134 | Not benchmarked | $0.35 | |
| 54 | MiniMax M2.7MiniMax | 1233 | Not published | 28.4 | $1.20 | |
| 55 | Gemini 3.1 Pro PreviewGoogle | 1231 | 47,246 | 35.3 | $12.00 | |
| 56 | GPT-5.6 LunaOpenAI | 1231 | 21,772 | 61.5 | $1.20 | |
| 57 | DeepSeek V4 Flash 0731DeepSeek | 1230 | 10,439 | Not benchmarked | $1.32 | |
| 58 | GLM 5V TurboZ.ai | 1228 | 47,181 | 28.8 | $4.00 | |
| 59 | Hy3Tencent | 1227 | 29,381 | 43.9 | $0.528 | |
| 60 | Grok 4.20xAI | 1222 | Not published | Not benchmarked | $2.50 | |
| 61 | GLM 4.7Z.ai | 1217 | 46,849 | 33.6 | $1.98 | |
| 62 | MiniMax M2.5MiniMax | 1207 | Not published | 59.4 | $0.95 | |
| 63 | T InklingThinking Machines | 1206 | 18,796 | 49.7 | $4.05 | |
| 64 | DeepSeek V4 Flash 0423DeepSeek | 1205 | 28,103 | 54.6 | $0.182 | |
| 65 | MiniMax M2.1MiniMax | 1191 | 20,808 | Not benchmarked | $1.20 | |
| 66 | Gemini 3 Flash PreviewGoogle | 1189 | 4,414 | 75.8 | $3.00 | |
| 67 | Grok 4.3xAI | 1187 | 41,178 | 22.5 | $2.50 | |
| 68 | Claude Sonnet 4.5Anthropic | 1183 | 45,448 | 59.1 | $15.00 | |
| 69 | Step 3.7 FlashStepFun | 1182 | 30,001 | Not benchmarked | $1.15 | |
| 70 | Solar Pro 4Upstage | 1182 | 17,878 | 24.4 | $0.60 | |
| 71 | GPT-5.4OpenAI | 1180 | 21,154 | 37.7 | $15.00 | |
| 72 | Qwen3.5 397B A17BQwen | 1180 | 8,130 | 28.6 | $2.34 | |
| 73 | GLM 4.7 FlashZ.ai | 1178 | 11,706 | Not benchmarked | $0.40 | |
| 74 | DeepSeek V3.1 TerminusDeepSeek | 1175 | Not published | Not benchmarked | $1.00 | |
| 75 | Claude Opus 4.1Anthropic | 1171 | 15,715 | 27.2 | $75.00 | |
| 76 | DeepSeek V3.2 ExpDeepSeek | 1171 | 19,487 | 55.0 | $0.41 | |
| 77 | GPT-5.1OpenAI | 1171 | 16,116 | 53.3 | $10.00 | |
| 78 | GPT-5.2OpenAI | 1171 | Not published | 58.9 | $14.00 | |
| 79 | GPT-5OpenAI | 1168 | 13,485 | 72.2 | $10.00 | |
| 80 | Qwen3.5 Plus 2026-02-15Qwen | 1167 | 18,504 | Not benchmarked | $1.56 | |
| 81 | GLM 4.6Z.ai | 1166 | 17,086 | 52.2 | $2.20 | |
| 82 | GLM 4.5Z.ai | 1165 | 19,653 | 64.2 | $2.20 | |
| 83 | DeepSeek V3.2DeepSeek | 1164 | 29,125 | 54.4 | $0.42 | |
| 84 | Nemotron 3.5 Super VLNVIDIA | 1155 | 2,826 | 65.5 | $0.50 | |
| 85 | GPT-5.1-CodexOpenAI | 1153 | 2,005 | 50.5 | $10.00 | |
| 86 | Gemini 2.5 ProGoogle | 1152 | 7,220 | 37.0 | $10.00 | |
| 87 | Solar Mini 4Upstage | 1152 | 2,128 | Not benchmarked | $0.20 | |
| 88 | Nemotron 3 UltraNVIDIA | 1147 | 25,884 | Not benchmarked | $2.40 | |
| 89 | GPT-5.3-CodexOpenAI | 1145 | 15,677 | 29.5 | $14.00 | |
| 90 | Qwen3 Coder 480B A35BQwen | 1143 | 1,955 | 50.0 | $1.00 | |
| 91 | Mistral Large 3 2512Mistral AI | 1142 | 30,430 | Not benchmarked | $1.50 | |
| 92 | R1 0528DeepSeek | 1139 | 17,951 | 71.4 | $2.15 | |
| 93 | GLM 4.5 AirZ.ai | 1137 | 17,253 | Not benchmarked | $0.85 | |
| 94 | MiniMax M2MiniMax | 1135 | Not published | 45.3 | $1.02 | |
| 95 | Mistral Medium 3.5Mistral AI | 1122 | 10,894 | 9.2 | $7.50 | |
| 96 | Mistral Medium 3.1Mistral AI | 1120 | 27,828 | Not benchmarked | $2.00 | |
| 97 | Trinity Large ThinkingArcee AI | 1117 | 12,840 | 5.4 | $0.80 | |
| 98 | Claude Haiku 4.5Anthropic | 1115 | 35,541 | 49.8 | $5.00 | |
| 99 | GPT-5 MiniOpenAI | 1115 | 37,100 | 59.8 | $2.00 | |
| 100 | DeepSeek V3.1DeepSeek | 1113 | Not published | Not benchmarked | $0.95 | |
| 101 | DeepSeek V3DeepSeek | 1108 | 19,271 | 70.2 | $1.0287 | |
| 102 | Kimi K2 0905Moonshot AI | 1098 | Not published | Not benchmarked | $2.50 | |
| 103 | GPT-5.1-Codex-MiniOpenAI | 1094 | 33,839 | 6.2 | $2.00 | |
| 104 | GPT-5 NanoOpenAI | 1084 | 6,703 | 34.8 | $0.40 | |
| 105 | Gemini 3.1 Flash Lite PreviewGoogle | 1072 | 23,538 | 8.1 | $1.50 | |
| 106 | Mistral Medium 3Mistral AI | 1069 | 6,390 | Not benchmarked | $2.00 | |
| 107 | Ministral 3 14B 2512Mistral AI | 1065 | 2,380 | Not benchmarked | $0.20 | |
| 108 | Gemini 2.5 FlashGoogle | 1059 | 6,971 | 28.7 | $2.50 | |
| 109 | Ministral 3 8B 2512Mistral AI | 1053 | 2,427 | Not benchmarked | $0.15 | |
| 110 | Qwen3 235B A22B Instruct 2507Qwen | 1039 | 6,939 | Not benchmarked | $0.55 | |
| 111 | Kimi K2 0711Moonshot AI | 1034 | 1,352 | 64.7 | $2.30 | |
| 112 | Qwen3 235B A22B Thinking 2507Qwen | 1033 | 6,175 | Not benchmarked | $3.50 | |
| 113 | GPT-4.1OpenAI | 1026 | 1,747 | 46.5 | $8.00 | |
| 114 | Mercury 2Inception | 1022 | 25,300 | 0.0 | $0.75 | |
| 115 | o3OpenAI | 1021 | Not published | 70.7 | $8.00 | |
| 116 | Ministral 3 3B 2512Mistral AI | 1010 | 2,852 | Not benchmarked | $0.10 | |
| 117 | Codestral 2508Mistral AI | 1007 | 6,734 | Not benchmarked | $0.90 | |
| 118 | GPT-4.1 MiniOpenAI | 994 | 1,566 | 28.5 | $1.60 | |
| 119 | o4 MiniOpenAI | 977 | Not published | 68.6 | $4.40 | |
| 120 | GPT-4.1 NanoOpenAI | 963 | 1,901 | 8.9 | $0.40 | |
| 121 | gpt-oss-120bOpenAI | 963 | 5,272 | 34.5 | $0.60 | |
| 122 | Qwen3 30B A3BQwen | 942 | 2,568 | Not benchmarked | $0.50 | |
| 123 | Mistral Small 3.2 24BMistral AI | 907 | Not published | Not benchmarked | $0.25 | |
| 124 | Llama 4 MaverickMeta Llama | 880 | 1,678 | 18.1 | $0.6525 | |
| 125 | GPT-4oOpenAI | 861 | 1,780 | 38.8 | $10.00 | |
| 126 | Llama 4 ScoutMeta Llama | 790 | 1,275 | 9.1 | $0.30 |
Only models in our catalog are listed, and each appears once with its best published run. 141 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.