Updated daily at 05:00 UTC
Benchmark
Vision Arena (arena.ai)
Measures: Users upload an image with a prompt, two anonymous multimodal models answer, and the user votes; votes are turned into an Elo-scale score with a confidence interval, style-controlled by default.
- Maintainer
- Arena Intelligence (arena.ai; formerly LMArena / LMSYS Chatbot Arena)
- Introduced
- 2024
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.
| Model | Arena score (Elo scale) | Score CI (+/-) | Votes | Provenance | Source | Evaluated |
|---|---|---|---|---|---|---|
| Claude Fable 5 Anthropic · High effort | 1310 | — | 13483 | Independent | Arena | 28 Sep 2026 |
| Qwen3.8-Max Alibaba Group · Max effort | 1301 | — | 10086 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.6 Anthropic · High effort | 1299 | — | 22350 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.7 | 1299 | — | 22948 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.7 Anthropic · High effort | 1298 | — | 22559 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.7 Flash Google DeepMind · High effort | 1295 | — | 3425 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.6 | 1295 | — | 26904 | Independent | Arena | 28 Sep 2026 |
| Muse Spark 1.3 Meta · Max effort | 1290 | — | 3472 | Independent | Arena | 28 Sep 2026 |
| Gemini 3 Pro | 1289 | — | 13624 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 5 Anthropic · High effort | 1289 | — | 15304 | Independent | Arena | 28 Sep 2026 |
| GPT-5.6 Sol OpenAI · Xhigh effort | 1287 | — | 10063 | Independent | Arena | 28 Sep 2026 |
| Claude Fable 5.1 Anthropic · Max effort | 1287 | — | 4050 | Independent | Arena | 28 Sep 2026 |
| GPT-5.5 | 1287 | — | 26870 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.8 Anthropic · High effort | 1286 | — | 18020 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.8 Flash Google DeepMind · High effort | 1286 | — | 2711 | Independent | Arena | 28 Sep 2026 |
| GPT-6 Astra OpenAI · Max effort | 1285 | — | 2869 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.5 Flash Google DeepMind · High effort | 1285 | — | 11983 | Independent | Arena | 28 Sep 2026 |
| GPT-5.4 OpenAI · High effort | 1284 | — | 28881 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.5 Flash Google DeepMind · Medium effort | 1284 | — | 12124 | Independent | Arena | 28 Sep 2026 |
| GLM-5.3-Flash | 1281 | — | 4832 | Independent | Arena | 28 Sep 2026 |
| GPT-5.5 OpenAI · High effort | 1281 | — | 25170 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.6 Flash Google DeepMind · High effort | 1280 | — | 7076 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.1 Pro | 1280 | — | 45204 | Independent | Arena | 28 Sep 2026 |
| Muse Spark 1.1 | 1280 | — | 10906 | Independent | Arena | 28 Sep 2026 |
| GPT-5.4 | 1279 | — | 22854 | Independent | Arena | 28 Sep 2026 |
| Grok 4.5 | 1279 | — | 10681 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4.8 | 1279 | — | 18583 | Independent | Arena | 28 Sep 2026 |
| GPT-5.2 Instant (gpt-5.2-chat-latest) | 1278 | — | 16492 | Independent | Arena | 28 Sep 2026 |
| Claude Sonnet 4.6 | 1275 | — | 27465 | Independent | Arena | 28 Sep 2026 |
| Gemini 3 Flash | 1273 | — | 39181 | Independent | Arena | 28 Sep 2026 |
| GPT-5.6 Terra OpenAI · Xhigh effort | 1268 | — | 9990 | Independent | Arena | 28 Sep 2026 |
| Qwen3.7-Plus | 1266 | — | 12799 | Independent | Arena | 28 Sep 2026 |
| Kimi K2.6 | 1265 | — | 16416 | Independent | Arena | 28 Sep 2026 |
| Claude Sonnet 5 Anthropic · High effort | 1265 | — | 12722 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.5 Flash-Lite | 1264 | — | 7200 | Independent | Arena | 28 Sep 2026 |
| Grok 4.6 SpaceXAI (xAI) · High effort | 1263 | — | 5374 | Independent | Arena | 28 Sep 2026 |
| Gemma 4 31B | 1263 | — | 38935 | Independent | Arena | 28 Sep 2026 |
| GPT-5.6 Luna OpenAI · Xhigh effort | 1259 | — | 10099 | Independent | Arena | 28 Sep 2026 |
| Grok 4.20 SpaceXAI (xAI) · Reasoning effort | 1256 | — | 26870 | Independent | Arena | 28 Sep 2026 |
| MiMo-V2.6-Flash | 1253 | — | 1865 | Independent | Arena | 28 Sep 2026 |
| Kimi K2.5 Moonshot AI · Thinking effort | 1252 | — | 28367 | Independent | Arena | 28 Sep 2026 |
| GPT-5.1 OpenAI · High effort | 1251 | — | 9843 | Independent | Arena | 28 Sep 2026 |
| GPT-5.4 mini OpenAI · High effort | 1251 | — | 25775 | Independent | Arena | 28 Sep 2026 |
| Grok 4.20 Multi-Agent | 1250 | — | 24597 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.5 Pro | 1247 | — | 88831 | Independent | Arena | 28 Sep 2026 |
| MiMo-V2.6-Pro | 1246 | — | 1802 | Independent | Arena | 28 Sep 2026 |
| Qwen3.5-397B-A17B | 1245 | — | 31178 | Independent | Arena | 28 Sep 2026 |
| Grok 4.3 | 1244 | — | 25944 | Independent | Arena | 28 Sep 2026 |
| GPT-5.2 OpenAI · High effort | 1243 | — | 19051 | Independent | Arena | 28 Sep 2026 |
| Qwen3.8-27B | 1242 | — | 6147 | Independent | Arena | 28 Sep 2026 |
| Gemma 4 26B A4B | 1242 | — | 23977 | Independent | Arena | 28 Sep 2026 |
| GPT-5.1 | 1240 | — | 10798 | Independent | Arena | 28 Sep 2026 |
| ChatGPT-4o | 1239 | — | 23429 | Independent | Arena | 28 Sep 2026 |
| MiniMax-M3 | 1237 | — | 17970 | Independent | Arena | 28 Sep 2026 |
| Gemini 3.1 Flash-Lite | 1235 | — | 27719 | Independent | Arena | 28 Sep 2026 |
| MiMo-V2.5 | 1232 | — | 27858 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.5 Flash | 1230 | — | 4793 | Independent | Arena | 28 Sep 2026 |
| GLM-5V-Turbo | 1230 | — | 41294 | Independent | Arena | 28 Sep 2026 |
| GPT-5.2 | 1229 | — | 20149 | Independent | Arena | 28 Sep 2026 |
| Qwen3.5-122B-A10B | 1226 | — | 13259 | Independent | Arena | 28 Sep 2026 |
| GPT-5 Instant (gpt-5-chat-latest) | 1225 | — | 39918 | Independent | Arena | 28 Sep 2026 |
| GPT-4.5 | 1225 | — | 2925 | Independent | Arena | 28 Sep 2026 |
| Qwen3.5-27B | 1217 | — | 28689 | Independent | Arena | 28 Sep 2026 |
| MiMo-V2-Omni | 1216 | — | 10687 | Independent | Arena | 28 Sep 2026 |
| o3 | 1216 | — | 45606 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.5 Flash | 1215 | — | 60141 | Independent | Arena | 28 Sep 2026 |
| Qwen3-VL-235B-A22B-Instruct | 1215 | — | 12734 | Independent | Arena | 28 Sep 2026 |
| GPT-4.1 | 1214 | — | 41027 | Independent | Arena | 28 Sep 2026 |
| GPT-5 OpenAI · High effort | 1210 | — | 34464 | Independent | Arena | 28 Sep 2026 |
| Inkling Small | 1207 | — | 6658 | Independent | Arena | 28 Sep 2026 |
| GPT-4.1 mini | 1201 | — | 40235 | Independent | Arena | 28 Sep 2026 |
| o4-mini | 1201 | — | 41354 | Independent | Arena | 28 Sep 2026 |
| Mistral Large 3 | 1200 | — | 7880 | Independent | Arena | 28 Sep 2026 |
| Mistral Medium 3.5 | 1200 | — | 5391 | Independent | Arena | 28 Sep 2026 |
| GPT-5.4 nano OpenAI · High effort | 1200 | — | 25685 | Independent | Arena | 28 Sep 2026 |
| Grok 4.1 Fast SpaceXAI (xAI) · Reasoning effort | 1196 | — | 13401 | Independent | Arena | 28 Sep 2026 |
| o1 | 1193 | — | 3694 | Independent | Arena | 28 Sep 2026 |
| Claude Opus 4 | 1188 | — | 2177 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.5 Flash-Lite Google DeepMind · Thinking effort | 1188 | — | 35953 | Independent | Arena | 28 Sep 2026 |
| Qwen3-VL-235B-A22B-Thinking Alibaba Group · Thinking effort | 1188 | — | 2389 | Independent | Arena | 28 Sep 2026 |
| Claude Sonnet 4 | 1188 | — | 1808 | Independent | Arena | 28 Sep 2026 |
| Qwen-VL-Max | 1185 | — | 3173 | Independent | Arena | 28 Sep 2026 |
| Grok 4 | 1184 | — | 30195 | Independent | Arena | 28 Sep 2026 |
| GPT-5 mini OpenAI · High effort | 1183 | — | 28971 | Independent | Arena | 28 Sep 2026 |
| Gemini 1.5 Pro | 1179 | — | 8902 | Independent | Arena | 28 Sep 2026 |
| Claude 3.7 Sonnet | 1175 | — | 4519 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.0 Flash | 1172 | — | 10137 | Independent | Arena | 28 Sep 2026 |
| GPT-4o | 1162 | — | 23273 | Independent | Arena | 28 Sep 2026 |
| GLM-4.6V | 1161 | — | 2455 | Independent | Arena | 28 Sep 2026 |
| Claude 3.5 Sonnet | 1161 | — | 10376 | Independent | Arena | 28 Sep 2026 |
| Gemma 3 27B | 1160 | — | 16991 | Independent | Arena | 28 Sep 2026 |
| Mistral Medium 3.1 | 1159 | — | 41647 | Independent | Arena | 28 Sep 2026 |
| Mistral Medium 3 | 1155 | — | 10810 | Independent | Arena | 28 Sep 2026 |
| GLM-4.5V | 1153 | — | 3249 | Independent | Arena | 28 Sep 2026 |
| GPT-5 nano OpenAI · High effort | 1146 | — | 3934 | Independent | Arena | 28 Sep 2026 |
| Llama 4 Maverick | 1145 | — | 6925 | Independent | Arena | 28 Sep 2026 |
| Claude 3.5 Sonnet | 1145 | — | 21624 | Independent | Arena | 28 Sep 2026 |
| Step3 | 1145 | — | 3199 | Independent | Arena | 28 Sep 2026 |
| Gemini 1.5 Flash | 1141 | — | 7241 | Independent | Arena | 28 Sep 2026 |
| Mistral Small 3.2 | 1140 | — | 10848 | Independent | Arena | 28 Sep 2026 |
| Gemini 2.0 Flash-Lite | 1136 | — | 3991 | Independent | Arena | 28 Sep 2026 |
| Llama 4 Scout | 1127 | — | 6455 | Independent | Arena | 28 Sep 2026 |
| Mistral Small 3.1 | 1127 | — | 28507 | Independent | Arena | 28 Sep 2026 |
| Claude 3.5 Haiku | 1127 | — | 1400 | Independent | Arena | 28 Sep 2026 |
| Qwen2.5-VL-72B-Instruct | 1121 | — | 3768 | Independent | Arena | 28 Sep 2026 |
| Gemini 1.5 Pro | 1120 | — | 16734 | Independent | Arena | 28 Sep 2026 |
| Qwen2.5-VL-32B-Instruct | 1119 | — | 1490 | Independent | Arena | 28 Sep 2026 |
| GPT-4o | 1118 | — | 3376 | Independent | Arena | 28 Sep 2026 |
| GPT-4 Turbo | 1112 | — | 13391 | Independent | Arena | 28 Sep 2026 |
| GPT-4o mini | 1097 | — | 17341 | Independent | Arena | 28 Sep 2026 |
| Pixtral Large | 1095 | — | 5423 | Independent | Arena | 28 Sep 2026 |
| GPT-4.1 nano | 1089 | — | 1211 | Independent | Arena | 28 Sep 2026 |
| Gemini 1.5 Flash-8B | 1071 | — | 6243 | Independent | Arena | 28 Sep 2026 |
| Step-1V | 1064 | — | 1534 | Independent | Arena | 28 Sep 2026 |
| Claude 3 Opus | 1062 | — | 15565 | Independent | Arena | 28 Sep 2026 |
| Gemini 1.5 Flash | 1060 | — | 13260 | Independent | Arena | 28 Sep 2026 |
| Molmo 72B | 1045 | — | 3048 | Independent | Arena | 28 Sep 2026 |
| Qwen2-VL-7B-Instruct | 1031 | — | 5766 | Independent | Arena | 28 Sep 2026 |
| Pixtral 12B | 1025 | — | 7511 | Independent | Arena | 28 Sep 2026 |
| InternVL2-26B | 1025 | — | 5148 | Independent | Arena | 28 Sep 2026 |
| Claude 3 Sonnet | 1016 | — | 12314 | Independent | Arena | 28 Sep 2026 |
| Aya Vision 32B | 1000 | — | 847 | Independent | Arena | 28 Sep 2026 |
| Claude 3 Haiku | 1000 | — | 13380 | Independent | Arena | 28 Sep 2026 |
| Molmo 7B-D | 994 | — | 2815 | Independent | Arena | 28 Sep 2026 |
| CogVLM2-Llama3-Chat-19B | 964 | — | 1991 | Independent | Arena | 28 Sep 2026 |
| MiniCPM-V-2.6 | 963 | — | 1987 | Independent | Arena | 28 Sep 2026 |
| InternVL2-4B | 958 | — | 3703 | Independent | Arena | 28 Sep 2026 |
| Phi-3.5-vision | 920 | — | 2592 | Independent | Arena | 28 Sep 2026 |
| Phi-3-vision | 881 | — | 1401 | Independent | Arena | 28 Sep 2026 |
- Arena (arena.ai), lmarena-ai/leaderboard-dataset, CC BY 4.0.