LMArena Vision leaderboard
- Claude Fable 5 leads
- 1325
- models measured
- 85
- lead over #2
- +4 Elo
- median
- 1257
Leader on LMArena Vision · read October 21
On October 21, 2026, 85 of our catalog's models had a LMArena Vision result, and Anthropic Claude Fable 5 led with 1325.
Prompts that come with an image. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena 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 | Votes | Interval (±) | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5Anthropic | 1325 | 14,714 | ±7.0 | 82.1 | $50.00 | |
| 2 | Claude Opus 5.5Anthropic | 1321 | 3,035 | ±11.7 | 92.2 | $20.00 | |
| 3 | Claude Opus 5Anthropic | 1320 | 17,743 | ±6.6 | 81.8 | $25.00 | |
| 4 | Claude Fable 5.1Anthropic | 1319 | 5,026 | ±9.3 | 89.1 | $50.00 | |
| 5 | Claude Opus 4.7Anthropic | 1317 | 23,139 | ±6.5 | 51.1 | $25.00 | |
| 6 | Claude Opus 4.6Anthropic | 1316 | 22,286 | ±6.4 | 66.9 | $25.00 | |
| 7 | Gemini 3.8 FlashGoogle | 1315 | 4,645 | ±9.7 | 70.5 | $4.125 | |
| 8 | Gemini 3.7 FlashGoogle | 1314 | 5,369 | ±9.2 | 69.9 | $3.75 | |
| 9 | Qwen3.8 Max (0902)Qwen | 1313 | 9,957 | ±7.5 | 63.5 | $6.00 | |
| 10 | Muse Spark 1.3Meta | 1308 | 5,392 | ±9.2 | 79.7 | $4.25 | |
| 11 | Gemini 3.5 FlashGoogle | 1308 | 13,862 | ±6.8 | 42.8 | $9.00 | |
| 12 | Muse Spark 1.2Meta | 1304 | 1,948 | ±14.3 | 65.1 | $4.25 | |
| 13 | GPT-5.4OpenAI | 1303 | 30,747 | ±5.7 | 37.7 | $15.00 | |
| 14 | Gemini 3.6 FlashGoogle | 1299 | 8,979 | ±7.9 | 48.3 | $3.75 | |
| 15 | GPT-5.5OpenAI | 1297 | 28,781 | ±5.8 | 67.8 | $30.00 | |
| 16 | Gemini 3.1 Pro PreviewGoogle | 1296 | 47,114 | ±5.1 | 35.3 | $12.00 | |
| 17 | Claude Opus 4.8Anthropic | 1294 | 18,303 | ±6.5 | 66.0 | $25.00 | |
| 18 | GLM 5.3 FlashZ.ai | 1294 | 16,254 | ±6.4 | 71.0 | $0.50 | |
| 19 | Muse Spark 1.1Meta | 1293 | 12,804 | ±6.9 | 48.9 | $4.25 | |
| 20 | GPT-6.1 SolOpenAI | 1288 | 2,330 | ±12.9 | 88.7 | $10.00 | |
| 21 | Claude Sonnet 5.5Anthropic | 1287 | 2,564 | ±12.5 | 88.9 | $10.00 | |
| 22 | Grok 4.5xAI | 1287 | 12,599 | ±7.0 | 75.5 | $6.00 | |
| 23 | Claude Sonnet 4.6Anthropic | 1283 | 27,408 | ±6.1 | 57.8 | $15.00 | |
| 24 | Kimi K2.6Moonshot AI | 1282 | 16,368 | ±6.8 | 44.2 | $3.41 | |
| 25 | GPT-5.6 SolOpenAI | 1281 | 11,439 | ±7.3 | 76.7 | $20.00 | |
| 26 | GPT-6 AstraOpenAI | 1280 | 4,012 | ±10.3 | 88.7 | $50.00 | |
| 27 | Qwen3.7 PlusQwen | 1278 | 14,212 | ±6.7 | Not benchmarked | $1.28 | |
| 28 | DeepSeek V4.1 FlashDeepSeek | 1278 | 4,100 | ±10.2 | 77.2 | $0.525 | |
| 29 | Gemma 4 31BGoogle | 1276 | 40,219 | ±5.7 | 38.3 | $0.40 | |
| 30 | Claude Sonnet 5Anthropic | 1273 | 14,034 | ±6.8 | 63.5 | $10.00 | |
| 31 | Mistral Large 4Mistral AI | 1272 | 1,008 | ±19.2 | 55.3 | $4.18 | |
| 32 | GPT-5.6 TerraOpenAI | 1271 | 11,842 | ±7.2 | 69.0 | $12.00 | |
| 33 | Qwen3.8 27BQwen | 1269 | 7,614 | ±8.2 | 73.6 | $1.35 | |
| 34 | Gemini 3.5 Flash LiteGoogle | 1269 | 9,238 | ±7.8 | 33.6 | $2.50 | |
| 35 | Kimi K2.5Moonshot AI | 1269 | 28,249 | ±5.7 | 58.5 | $2.50 | |
| 36 | Step 5 PreviewStepFun | 1265 | 1,649 | ±15.0 | 71.4 | $2.70 | |
| 37 | GLM 5V TurboZ.ai | 1264 | 42,757 | ±5.4 | 28.8 | $4.00 | |
| 38 | Gemini 2.5 ProGoogle | 1263 | 88,755 | ±4.5 | 37.0 | $10.00 | |
| 39 | Grok 4.6xAI | 1263 | 7,261 | ±8.3 | 76.4 | $6.00 | |
| 40 | MiMo-V2.6-ProXiaomi | 1263 | 1,754 | ±14.7 | 72.6 | $0.87 | |
| 41 | Qwen3.5 397B A17BQwen | 1262 | 32,657 | ±5.3 | 28.6 | $2.34 | |
| 42 | Gemma 4 26B A4BGoogle | 1260 | 23,922 | ±6.4 | 22.8 | $0.255 | |
| 43 | GPT-5.6 LunaOpenAI | 1257 | 11,055 | ±7.4 | 61.5 | $1.20 | |
| 44 | MiMo-V2.6-FlashXiaomi | 1256 | 3,618 | ±10.8 | 61.9 | $0.28 | |
| 45 | MiniMax M3MiniMax | 1251 | 19,844 | ±6.3 | 57.8 | $1.20 | |
| 46 | GPT-5.1OpenAI | 1250 | 9,848 | ±7.8 | 53.3 | $10.00 | |
| 47 | MiMo-V2.5Xiaomi | 1247 | 29,381 | ±5.8 | 34.0 | $0.238 | |
| 48 | Qwen3 VL 235B A22B InstructQwen | 1247 | 12,724 | ±6.9 | Not benchmarked | $1.90 | |
| 49 | GPT-5.2OpenAI | 1246 | 19,022 | ±6.0 | 58.9 | $14.00 | |
| 50 | GPT-5.4 MiniOpenAI | 1245 | 25,734 | ±6.2 | 28.2 | $4.50 | |
| 51 | Qwen3.5-122B-A10BQwen | 1244 | 13,236 | ±6.8 | 22.9 | $2.08 | |
| 52 | Qwen3.5-27BQwen | 1241 | 30,272 | ±5.5 | 22.6 | $2.16 | |
| 53 | Gemini 3.1 Flash Lite PreviewGoogle | 1240 | 27,657 | ±5.7 | 8.1 | $1.50 | |
| 54 | GPT-6 SolOpenAI | 1240 | 3,221 | ±11.3 | 82.8 | $10.00 | |
| 55 | T Inkling SmallThinking Machines | 1237 | 8,074 | ±8.1 | 29.9 | $1.20 | |
| 56 | Gemini 2.5 FlashGoogle | 1235 | 60,087 | ±4.5 | 28.7 | $2.50 | |
| 57 | GPT-5OpenAI | 1232 | 39,894 | ±7.0 | 72.2 | $10.00 | |
| 58 | Grok 4.7xAI | 1231 | 3,736 | ±10.6 | 75.0 | $6.00 | |
| 59 | Grok 4.3xAI | 1229 | 27,901 | ±5.8 | 22.5 | $2.50 | |
| 60 | Mistral Medium 3.5Mistral AI | 1222 | 5,375 | ±9.5 | 9.2 | $7.50 | |
| 61 | GPT-6 LunaOpenAI | 1216 | 3,662 | ±10.8 | 71.4 | $0.50 | |
| 62 | o3OpenAI | 1214 | 45,567 | ±6.5 | 70.7 | $8.00 | |
| 63 | GPT-4.1OpenAI | 1210 | 40,998 | ±6.7 | 46.5 | $8.00 | |
| 64 | GPT-5 MiniOpenAI | 1202 | 28,943 | ±7.8 | 59.8 | $2.00 | |
| 65 | GPT-5.4 NanoOpenAI | 1196 | 25,624 | ±6.3 | Not benchmarked | $1.25 | |
| 66 | o4 MiniOpenAI | 1194 | 41,316 | ±7.1 | 68.6 | $4.40 | |
| 67 | GPT-4.1 MiniOpenAI | 1181 | 40,201 | ±7.5 | 28.5 | $1.60 | |
| 68 | Mistral Medium 3.1Mistral AI | 1172 | 41,611 | ±6.2 | Not benchmarked | $2.00 | |
| 69 | o1OpenAI | 1168 | 3,694 | ±10.8 | 61.7 | $60.00 | |
| 70 | Gemma 3 27BGoogle | 1165 | 16,982 | ±8.0 | 4.9 | $0.35 | |
| 71 | GLM 4.6VZ.ai | 1164 | 2,455 | ±13.7 | Not benchmarked | $0.90 | |
| 72 | GPT-5 NanoOpenAI | 1159 | 3,928 | ±11.1 | 34.8 | $0.40 | |
| 73 | Mistral Medium 3Mistral AI | 1157 | 10,793 | ±8.3 | Not benchmarked | $2.00 | |
| 74 | GLM 4.5VZ.ai | 1154 | 3,243 | ±11.6 | Not benchmarked | $1.80 | |
| 75 | Llama 4 MaverickMeta Llama | 1142 | 6,923 | ±9.1 | 18.1 | $0.6525 | |
| 76 | GPT-4o (2024-05-13)OpenAI | 1137 | 23,273 | ±8.8 | Not benchmarked | $15.00 | |
| 77 | Mistral Small 3.1 24BMistral AI | 1136 | 28,490 | ±8.5 | Not benchmarked | $0.555 | |
| 78 | Llama 4 ScoutMeta Llama | 1118 | 6,446 | ±9.4 | 9.1 | $0.30 | |
| 79 | Qwen2.5 VL 72B InstructQwen | 1107 | 3,768 | ±10.9 | Not benchmarked | $1.00 | |
| 80 | GPT-4 TurboOpenAI | 1090 | 13,391 | ±11.6 | Not benchmarked | $30.00 | |
| 81 | GPT-4o-mini (2024-07-18)OpenAI | 1066 | 17,341 | ±8.3 | 3.6 | $0.60 | |
| 82 | GPT-4o (2024-08-06)OpenAI | 1065 | 3,376 | ±12.5 | 23.1 | $10.00 | |
| 83 | GPT-4.1 NanoOpenAI | 1063 | 1,211 | ±18.3 | 8.9 | $0.40 | |
| 84 | Nova Lite 1.0Amazon | 990 | 1,854 | ±15.0 | Not benchmarked | $0.24 | |
| 85 | Nova Pro 1.0Amazon | 980 | 2,335 | ±13.9 | Not benchmarked | $3.20 |
Only models in our catalog are listed, and each appears once with its best published run. 172 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.