Arena Vision — Homework (Style Controlled)
Multimodal
Style-controlled Vision Arena rating for visually grounded homework prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 1358 |
| Claude Fable 5 | 1352 |
| GPT-6 Astra | 1342 |
| Gemini 3.8 Flash | 1338 |
| GPT-5.5 | 1335 |
| Claude Fable 5.1 | 1334 |
| Qwen3.8-Max | 1334 |
| Opus 4.8 | 1332 |
| Opus 4.7 | 1331 |
| GPT-5.4 | 1330 |
| Claude Sonnet 5.5 | 1326 |
| Opus 4.6 | 1325 |
| Grok 4.7 | 1324 |
| Claude Opus 5 | 1323 |
| GPT-5.6 Terra | 1321 |
| Gemini 3.5 Flash | 1316 |
| GPT-5.6 Sol | 1314 |
| Gemini 3.1 Pro Preview | 1310 |
| Gemini 3.7 Flash | 1309 |
| Gemini 3 Pro Preview | 1309 |
| Gemini 3 Flash Preview | 1308 |
| DeepSeek V4.1 Flash | 1307 |
| GLM-5.3 Flash | 1306 |
| Sonnet 5 | 1305 |
| Gemma 4 31B IT | 1304 |
| Gemini 3.6 Flash | 1304 |
| Kimi K2.6 | 1302 |
| Sonnet 4.6 | 1302 |
| Grok 4.5 | 1299 |
| Muse Spark | 1299 |
| Muse Spark 1.3 | 1297 |
| Grok 4.6 | 1297 |
| GPT-5.4 Mini | 1291 |
| Gemini 3.5 Flash-Lite | 1290 |
| Kimi K2.5 | 1290 |
| GPT-5.6 Luna | 1290 |
| Qwen3.7-Plus (source unspecified) | 1289 |
| Muse Spark 1.1 | 1288 |
| Qwen3.5 397B A17B | 1287 |
| Gemma 4 26B A4B IT | 1285 |