Arena Vision — Humor (No Style Control)
Multimodal
Raw Vision Arena rating for visually grounded humor prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Muse Spark | 1344 |
| Claude Fable 5 | 1341 |
| Gemini 3 Pro Preview | 1339 |
| Gemini 3.1 Pro Preview | 1322 |
| Gemini 3.5 Flash | 1321 |
| Gemini 3.8 Flash | 1321 |
| Claude Fable 5.1 | 1318 |
| Opus 4.6 | 1314 |
| Opus 4.7 | 1309 |
| Qwen3.8-Max | 1304 |
| Gemini 3.7 Flash | 1299 |
| Claude Opus 5 | 1293 |
| Muse Spark 1.3 | 1293 |
| GPT-5.5 | 1293 |
| Gemini 3 Flash Preview | 1291 |
| Gemini 3.6 Flash | 1289 |
| Muse Spark 1.1 | 1288 |
| Gemini 3.5 Flash-Lite | 1287 |
| GPT-5.4 | 1284 |
| Kimi K2.5 | 1284 |
| Opus 4.8 | 1282 |
| Kimi K2.6 | 1280 |
| Gemma 4 31B IT | 1280 |
| GLM-5.3 Flash | 1279 |
| Grok 4.5 | 1276 |
| Gemma 4 26B A4B IT | 1272 |
| Grok 4.6 | 1270 |
| GLM 5V Turbo | 1268 |
| Gemini 3.1 Flash-Lite Preview | 1266 |
| GPT-5.1 | 1263 |
| Gemini 2.5 Pro | 1262 |
| Qwen3.5 397B A17B | 1262 |
| Qwen3.7-Plus (source unspecified) | 1261 |
| Sonnet 5 | 1261 |
| DeepSeek V4.1 Flash | 1260 |
| Gemini 2.5 Flash Preview (09-2025) | 1255 |
| Sonnet 4.6 | 1248 |
| GPT-5.6 Sol | 1246 |
| Qwen3.5 122B A10B | 1243 |
| Grok 4.1 Fast | 1239 |