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 | 1300 |
| Gemini 3 Flash Preview | 1298 |
| Gemini 3.1 Pro Preview | 1287 |
| Gemini 3.1 Flash-Lite Preview | 1277 |
| Opus 4.6 | 1269 |
| GPT-5 | 1257 |
| Gemini 2.5 Pro | 1252 |
| Opus 4.7 | 1246 |
| GPT-5.1 | 1241 |
| Grok 4 | 1236 |
| O3 (2025-04-16) | 1234 |
| Kimi K2.5 | 1230 |
| Qwen3.5 397B A17B | 1224 |
| Gemini 2.5 Flash | 1219 |
| O4 Mini (2025-04-16) | 1218 |
| GPT-5 Mini | 1207 |
| Grok 4.1 Fast | 1201 |
| GPT-4.1 Mini (2025-04-14) | 1199 |
| GPT-5.4 Mini | 1198 |
| Gemma 4 31B | 1198 |
| GPT-5.2 | 1191 |
| Gemini 2.5 Flash-Lite Preview 06-17 | 1185 |
| GLM 5V Turbo | 1184 |
| GPT-4.1 (2025-04-14) | 1183 |
| MiMo-V2.5 | 1175 |
| Gemma 3 27B IT | 1174 |
| Sonnet 4.6 | 1157 |
| Gemma 4 26B A4B | 1157 |
| Mistral Small 3.2 24B Instruct 2506 | 1134 |
| Mistral Medium 3.1 | 1132 |
| GPT-5.4 Nano | 1126 |
| Mistral Small 3.1 24B Instruct 2503 | 1125 |
| Mistral Medium 3 | 1123 |