Arena Vision — Humor (Style Controlled)
Multimodal
Style-controlled Vision Arena rating for visually grounded humor prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 1324 |
| Muse Spark | 1323 |
| Gemini 3 Pro Preview | 1317 |
| Gemini 3.1 Pro Preview | 1300 |
| Gemini 3.8 Flash | 1298 |
| Opus 4.6 | 1297 |
| Gemini 3.5 Flash | 1293 |
| Claude Fable 5.1 | 1291 |
| Opus 4.7 | 1290 |
| Qwen3.8-Max | 1290 |
| GPT-5.5 | 1281 |
| Gemini 3.5 Flash-Lite | 1278 |
| Gemini 3.7 Flash | 1275 |
| Muse Spark 1.3 | 1275 |
| Muse Spark 1.1 | 1275 |
| Grok 4.6 | 1271 |
| Opus 4.8 | 1270 |
| Gemini 3 Flash Preview | 1269 |
| Gemini 3.6 Flash | 1268 |
| Claude Opus 5 | 1265 |
| GPT-5.1 | 1264 |
| GPT-5.4 | 1264 |
| Grok 4.5 | 1263 |
| Kimi K2.5 | 1262 |
| Kimi K2.6 | 1261 |
| Gemma 4 31B IT | 1260 |
| GPT-5.6 Sol | 1257 |
| GLM-5.3 Flash | 1256 |
| Gemini 3.1 Flash-Lite Preview | 1250 |
| Sonnet 5 | 1249 |
| Gemini 2.5 Pro | 1247 |
| Gemma 4 26B A4B IT | 1245 |
| DeepSeek V4.1 Flash | 1243 |
| Qwen3.5 397B A17B | 1242 |
| Sonnet 4.6 | 1241 |
| Qwen3.7-Plus (source unspecified) | 1239 |
| GPT-5.4 Mini | 1237 |
| GPT-5.6 Terra | 1236 |
| Grok 4.3 | 1229 |
| Grok 4.1 Fast | 1227 |