Arena Vision — Entity Recognition (Style Controlled)
Multimodal
Style-controlled Vision Arena rating for visual entity-recognition prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3 Pro Preview | 1292 |
| Gemini 3 Flash Preview | 1290 |
| Gemini 3.1 Pro Preview | 1284 |
| Gemini 3.1 Flash-Lite Preview | 1271 |
| GPT-5 | 1261 |
| Gemini 2.5 Pro | 1251 |
| Opus 4.7 | 1242 |
| Opus 4.6 | 1237 |
| Grok 4 | 1236 |
| Kimi K2.5 | 1232 |
| o3 | 1231 |
| GPT-5.1 | 1228 |
| Gemini 2.5 Flash | 1221 |
| GPT-5.5 | 1219 |
| O4 Mini | 1219 |
| Grok 4.1 Fast | 1217 |
| GPT-5.4 | 1215 |
| Qwen3.5 397B A17B | 1211 |
| GPT-5 Mini | 1211 |
| Grok 4.3 | 1210 |
| GPT-5.2 | 1201 |
| GPT-5.4 Mini | 1198 |
| GPT-4.1 Mini | 1197 |
| Gemma 4 31B IT | 1196 |
| GPT-4.1 | 1184 |
| Gemini 2.5 Flash-Lite | 1183 |
| GLM 5V Turbo | 1175 |
| Gemma 3 27B IT | 1170 |
| Sonnet 4.6 | 1167 |
| MiMo-V2.5 | 1163 |
| MiniMax M3 | 1161 |
| Gemma 4 26B A4B IT | 1158 |
| Mistral Small 3.2 24B Instruct 2506 | 1134 |
| Mistral Small 3.1 24B Instruct 2503 | 1131 |
| Mistral Medium 3.1 | 1128 |
| Mistral Medium 3 | 1125 |
| GPT-5.4 Nano | 1116 |