LMArena Vision Elo Leaderboard
vision121 models · Updated October 2026
On the LMArena Vision Elo benchmark, Claude Fable 5 ranks #1 with a score of 1325, while GLM 5.3 Flash offers the best score-per-dollar at $0.17/1M output tokens. The full ranking, with cost per million tokens, is below.
💰 Best value
GLM 5.3 Flash — score 1294 at $0.17/1M output tokens
| # | Model | Score | Output / 1M | Context |
|---|---|---|---|---|
| 1 | Claude Fable 5Anthropic | 1325 | $50.00 | 1M |
| 2 | Claude Opus 5.5Anthropic | 1321 | $20.00 | 1M |
| 3 | Claude Opus 5Anthropic | 1320 | $25.00 | 1M |
| 4 | Claude Fable 5.1Anthropic | 1319 | $50.00 | 1M |
| 5 | Claude Opus 4.7Anthropic | 1317 | $25.00 | 1M |
| 6 | Claude Opus 4.6Anthropic | 1316 | $25.00 | 1M |
| 7 | Gemini 3.8 FlashGoogle | 1315 | $3.75 | 1M |
| 8 | Gemini 3.7 FlashGoogle | 1314 | $3.75 | 1M |
| 9 | Qwen3.8 MaxAlibaba | 1313 | $6.00 | 1M |
| 10 | Muse Spark 1.3Meta | 1308 | $4.25 | 1M |
| 11 | Gemini 3.5 FlashGoogle | 1308 | $9.00 | 1M |
| 12 | Muse SparkMeta AI | 1306 | — | — |
| 13 | Gemini 3 ProOpenCode | 1305 | $12.00 | 1M |
| 14 | Muse Spark 1.2Meta | 1304 | $4.25 | 1M |
| 15 | GPT-5.4OpenAI | 1303 | $15.00 | 1.1M |
| 16 | Gemini 3.6 FlashGoogle | 1299 | $3.75 | 1M |
| 17 | GPT-5.5OpenAI | 1297 | $30.00 | 1.1M |
| 18 | Gemini 3.1 Pro PreviewGoogle | 1296 | $12.00 | 1M |
| 19 | Claude Opus 4.8Anthropic | 1294 | $25.00 | 1M |
| 20 | GLM 5.3 FlashZ.ai | 1294 | $0.17 | 1M |
| 21 | Muse Spark 1.1Meta | 1293 | $4.25 | 1M |
| 22 | GPT-6.1 SolOpenAI | 1288 | $10.00 | 1.1M |
| 23 | Claude Sonnet 5.5Anthropic | 1287 | $10.00 | 1M |
| 24 | Grok 4.5SpaceXAI | 1287 | $6.00 | 500K |
| 25 | Gemini 3 FlashOpenCode | 1285 | $3.00 | 1M |
| 26 | Claude Sonnet 4.6Anthropic | 1283 | $15.00 | 1M |
| 27 | Kimi K2.6MoonshotAI | 1282 | $3.41 | 262K |
| 28 | GPT-5.6 SolOpenAI | 1281 | $20.00 | 1.1M |
| 29 | GPT-6 AstraOpenAI | 1280 | $50.00 | 1.1M |
| 30 | Qwen3.7 PlusAlibaba | 1278 | $1.60 | 1M |
| 31 | DeepSeek V4.1 FlashDeepSeek | 1278 | $0.50 | 1M |
| 32 | Gemma 4 31BGoogle | 1276 | $0.40 | 262K |
| 33 | Claude Sonnet 5Anthropic | 1273 | $10.00 | 1M |
| 34 | Mistral Large 4Mistral | 1272 | $2.10 | 1M |
| 35 | GPT-5.6 TerraOpenAI | 1271 | $12.00 | 1.1M |
| 36 | Qwen3.8 27BQwen | 1269 | $1.88 | 1M |
| 37 | Gemini 3.5 Flash LiteGoogle | 1269 | $2.50 | 1M |
| 38 | Kimi K2.5MoonshotAI | 1269 | $2.50 | 262K |
| 39 | GPT-5.2 ChatOpenAI | 1268 | $14.00 | 128K |
| 40 | Step 5 PreviewStepFun | 1265 | $2.70 | 1M |
| 41 | GLM 5V TurboZ.ai | 1264 | $4.00 | 203K |
| 42 | Gemini 2.5 ProGoogle | 1263 | $10.00 | 1M |
| 43 | Grok 4.6SpaceXAI | 1263 | $6.00 | 500K |
| 44 | MiMo-V2.6-ProXiaomi | 1263 | $0.87 | 1.1M |
| 45 | Qwen3.5 397B-A17BAlibaba | 1262 | $3.60 | 262K |
| 46 | grok-4.20-beta-0309-reasoning302.AI | 1262 | $6.00 | 2M |
| 47 | Gemma 4 26B A4BGoogle | 1260 | $0.23 | 262K |
| 48 | grok-4.20-multi-agent-beta-0309302.AI | 1259 | $6.00 | 2M |
| 49 | GPT-5.6 LunaOpenAI | 1257 | $1.20 | 1.1M |
| 50 | MiMo-V2.6-FlashXiaomi | 1256 | $0.28 | 1.1M |
| 51 | gemini-2.5-flash-preview-05-20Jiekou.AI | 1254 | $3.33 | 1M |
| 52 | MiniMax M3MiniMax | 1251 | $1.20 | 1M |
| 53 | GPT-5.5 InstantZenMux | 1250 | $30.00 | 400K |
| 54 | GPT-5.1OpenAI | 1250 | $10.00 | 400K |
| 55 | MiMo-V2.5Xiaomi | 1247 | $0.28 | 1.1M |
| 56 | Qwen3 VL 235B A22B InstructQwen | 1247 | $1.90 | 262K |
| 57 | GPT-5.2OpenAI | 1246 | $14.00 | 400K |
| 58 | GPT-5.4 MiniOpenAI | 1245 | $4.50 | 400K |
| 59 | Qwen3.5 122B-A10BAlibaba | 1245 | $3.20 | 262K |
| 60 | chatgpt-4o-latest302.AI | 1243 | $15.00 | 128K |
| 61 | Qwen3.5 27BAlibaba | 1241 | $2.40 | 262K |
| 62 | Gemini 3.1 Flash Lite PreviewGoogle | 1240 | $1.50 | 1M |
| 63 | GPT-6 SolOpenAI | 1240 | $10.00 | 1.1M |
| 64 | Inkling SmallThinking Machines | 1237 | $1.20 | 524K |
| 65 | Gemini 2.5 FlashGoogle | 1235 | $2.50 | 1M |
| 66 | GPT-5 ChatOpenAI | 1232 | $10.00 | 128K |
| 67 | Grok 4.7SpaceXAI | 1231 | $6.00 | 500K |
| 68 | Grok 4.3SpaceXAI | 1229 | $2.50 | 1M |
| 69 | MiMo-V2-OmniXiaomi | 1228 | $0.28 | 262K |
| 70 | Mistral Medium 3.5Mistral | 1222 | $7.50 | 262K |
| 71 | Mistral Large 3 2512Mistral | 1220 | $1.50 | 262K |
| 72 | GPT-6 LunaOpenAI | 1216 | $0.50 | 1.1M |
| 73 | o3OpenAI | 1214 | $8.00 | 200K |
| 74 | Qwen-VL MaxAlibaba | 1213 | $3.20 | 131K |
| 75 | GPT-4.1OpenAI | 1210 | $8.00 | 1M |
| 76 | Grok-4Poe | 1210 | $15.00 | 256K |
| 77 | GPT-5OpenAI | 1208 | $10.00 | 400K |
| 78 | Qwen3-VL 235B-A22BAlibaba | 1207 | $2.80 | 131K |
| 79 | GPT-5 MiniOpenAI | 1202 | $2.00 | 400K |
| 80 | Grok 4.1 FastOfox | 1201 | $0.50 | 2M |
| 81 | gemini-2.5-flash-lite-preview-06-17Jiekou.AI | 1198 | $0.36 | 1M |
| 82 | GPT-5.4 NanoOpenAI | 1196 | $1.25 | 400K |
| 83 | o4 MiniOpenAI | 1194 | $4.40 | 200K |
| 84 | Claude Opus 4Anthropic | 1192 | $75.00 | 200K |
| 85 | Claude Sonnet 4 (latest)Anthropic | 1191 | $15.00 | 200K |
| 86 | GPT-4.1 MiniOpenAI | 1181 | $1.60 | 1M |
| 87 | Step-3NanoGPT | 1176 | $0.65 | 66K |
| 88 | Mistral Medium 3.1Mistral | 1172 | $2.00 | 131K |
| 89 | Claude 3.7 SonnetHelicone | 1169 | $15.00 | 200K |
| 90 | o1OpenAI | 1168 | $60.00 | 200K |
| 91 | Gemma 3 27B ITCortecs | 1165 | $0.30 | 131K |
| 92 | GLM 4.6VZ.ai | 1164 | $0.90 | 131K |
| 93 | Gemini 1.5 ProGoogle DeepMind | 1161 | — | — |
| 94 | GPT-5 NanoOpenAI | 1159 | $0.40 | 400K |
| 95 | Gemini 2.0 FlashGoogle | 1158 | $0.40 | 1M |
| 96 | Mistral Medium 3Mistral | 1157 | $2.00 | 131K |
| 97 | GLM 4.5VZ.ai | 1154 | $1.80 | 66K |
| 98 | Qwen2.5 VL 32B InstructLLM Gateway | 1152 | $4.20 | 131K |
| 99 | Mistral Small 3.2Mistral | 1142 | $0.30 | 128K |
| 100 | Llama 4 Maverick 17B 128E InstructVertex | 1142 | $1.15 | 524K |
| 101 | Gemini 1.5 FlashNanoGPT | 1141 | $0.31 | 2M |
| 102 | GPT-4oOpenAI | 1137 | $10.00 | 128K |
| 103 | Mistral Small 31 24b InstructNanoGPT | 1136 | $0.30 | 128K |
| 104 | Claude 3.5 SonnetDigitalOcean | 1126 | $15.00 | 200K |
| 105 | Llama 4 Scout 17B 16E InstructAzure | 1118 | $0.78 | 128K |
| 106 | Qwen2.5-VL 72B InstructAlibaba | 1107 | $8.40 | 131K |
| 107 | Claude 3.5 HaikuHelicone | 1093 | $4.00 | 200K |
| 108 | GPT-4 TurboOpenAI | 1090 | $30.00 | 128K |
| 109 | Pixtral Large (latest)Mistral | 1089 | $6.00 | 128K |
| 110 | GPT-4o-miniOpenAI | 1066 | $0.60 | 128K |
| 111 | GPT-4.1 NanoOpenAI | 1063 | $0.40 | 1M |
| 112 | Claude 3 OpusLLM Gateway | 1023 | $75.00 | 200K |
| 113 | Pixtral 12BMistral | 1009 | $0.15 | 128K |
| 114 | Llama 3.2 90B Vision InstructVercel AI Gateway | 1000 | $0.72 | 128K |
| 115 | Aya Vision 32BCohere | 996 | — | 16K |
| 116 | Amazon Nova Lite 1.0NanoGPT | 990 | $0.24 | 300K |
| 117 | Claude 3 SonnetAnthropic | 984 | — | — |
| 118 | Amazon Nova Pro 1.0NanoGPT | 980 | $3.20 | 300K |
| 119 | Llama 3.2 11B Vision InstructMeta | 966 | $0.35 | 131K |
| 120 | Claude 3 HaikuAnthropic | 950 | $1.25 | 200K |
| 121 | Phi-3.5-vision instruct (128k)GitHub Models | 851 | $0.00 | 128K |
What does LMArena Vision Elo test?
Overview This dataset contains ALL in-the-wild conversation crowdsourced from Search Arena between March 18, 2025 and May 8, 2025. It includes 24,069 multi-turn conversations with search-LLMs across diverse intents, languages, and topics—alongs...
Frequently asked questions
What is the LMArena Vision Elo benchmark?
Overview This dataset contains ALL in-the-wild conversation crowdsourced from Search Arena between March 18, 2025 and May 8, 2025. It includes 24,069 multi-turn conversations with search-LLMs across diverse intents, languages, and topics—alongs...
Which model is best on LMArena Vision Elo?
Claude Fable 5 (Anthropic) currently leads the LMArena Vision Elo leaderboard with a score of 1325.
What is the best value model on LMArena Vision Elo?
GLM 5.3 Flash offers the best score-per-dollar on LMArena Vision Elo — a score of 1294 at $0.17 per 1M output tokens.
Pricing is indicative — confirm with the provider before production use. Updated October 2026.