Arena Vision — Captioning (Style Controlled)
Multimodal
Style-controlled Vision Arena rating for image-captioning prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.1 Pro Preview | 1282 |
| Gemini 3 Pro Preview | 1277 |
| GPT-5.2 | 1262 |
| Gemini 2.5 Pro | 1251 |
| GPT-5.1 | 1248 |
| Gemma 4 26B A4B IT | 1239 |
| Gemini 3 Flash Preview | 1234 |
| Gemini 3.1 Flash-Lite Preview | 1225 |
| Gemini 2.5 Flash | 1211 |
| GPT-4.1 | 1210 |
| Kimi K2.5 | 1198 |
| GPT-5 | 1196 |
| GPT-4.1 Mini | 1193 |
| O4 Mini | 1185 |
| o3 | 1183 |
| Gemini 2.5 Flash-Lite | 1182 |
| GLM 5V Turbo | 1180 |
| GPT-5 Mini | 1175 |
| Qwen3.5 397B A17B | 1174 |
| Grok 4 | 1170 |
| Gemma 4 31B IT | 1170 |
| Gemini 2.0 Flash | 1150 |
| Mistral Small 3.1 24B Instruct 2503 | 1133 |
| Mistral Medium 3.1 | 1130 |
| Gemma 3 27B IT | 1117 |
| Mistral Medium 3 | 1090 |
| Mistral Small 3.2 24B Instruct 2506 | 1050 |