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 |
|---|---|
| Claude Fable 5 | 1343 |
| Claude Opus 5 | 1341 |
| GPT-5.5 | 1339 |
| Opus 4.8 | 1338 |
| GPT-5.4 | 1329 |
| Opus 4.7 | 1329 |
| Gemini 3.5 Flash | 1325 |
| Grok 4.5 | 1325 |
| Opus 4.6 | 1324 |
| Sonnet 5 | 1314 |
| GPT-5.6 Terra | 1312 |
| GPT-5.6 Sol | 1312 |
| Gemini 3.1 Pro Preview | 1310 |
| Gemini 3 Pro Preview | 1309 |
| Gemini 3 Flash Preview | 1308 |
| Kimi K2.6 | 1302 |
| Sonnet 4.6 | 1301 |
| Muse Spark | 1300 |
| Gemma 4 31B | 1300 |
| GPT-5.4 Mini | 1292 |
| Kimi K2.5 | 1290 |
| Gemma 4 26B A4B | 1284 |
| GPT-5.2 | 1283 |
| GPT-5.1 | 1282 |
| Qwen3.5 397B A17B | 1282 |
| GPT-5.6 Luna | 1278 |
| Muse Spark 1.1 | 1277 |
| Qwen3.7-Plus | 1277 |
| Gemini 2.5 Pro | 1272 |
| Gemini 3.1 Flash-Lite Preview | 1270 |
| Gemini 2.5 Flash Preview (09-2025) | 1266 |
| MiniMax M3 | 1264 |
| MiMo-V2.5 | 1262 |
| GPT-5 | 1260 |
| Grok 4.3 | 1255 |
| GLM 5V Turbo | 1254 |
| Qwen3.5 122B A10B | 1253 |
| O4 Mini (2025-04-16) | 1251 |
| GPT-4.1 (2025-04-14) | 1249 |
| O3 (2025-04-16) | 1247 |