Arena Vision — Homework (No Style Control)
Multimodal
Raw Vision Arena rating for visually grounded homework prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 1357 |
| Claude Fable 5 | 1353 |
| Opus 4.8 | 1343 |
| Gemini 3.5 Flash | 1338 |
| Opus 4.6 | 1336 |
| Opus 4.7 | 1335 |
| GPT-5.5 | 1335 |
| GPT-5.4 | 1335 |
| Grok 4.5 | 1322 |
| Sonnet 5 | 1321 |
| Gemini 3.1 Pro Preview | 1317 |
| Gemini 3 Pro Preview | 1315 |
| Gemini 3 Flash Preview | 1312 |
| Sonnet 4.6 | 1310 |
| Kimi K2.6 | 1310 |
| Gemma 4 31B | 1306 |
| GPT-5.6 Terra | 1304 |
| GPT-5.6 Sol | 1303 |
| Muse Spark | 1300 |
| Kimi K2.5 | 1297 |
| Gemma 4 26B A4B | 1292 |
| Qwen3.5 397B A17B | 1287 |
| GPT-5.4 Mini | 1287 |
| Qwen3.7-Plus | 1283 |
| Gemini 2.5 Pro | 1281 |
| Gemini 2.5 Flash Preview (09-2025) | 1279 |
| GPT-5.2 | 1278 |
| Muse Spark 1.1 | 1277 |
| GLM 5V Turbo | 1274 |
| MiniMax M3 | 1273 |
| GPT-5.6 Luna | 1271 |
| GPT-5.1 | 1271 |
| MiMo-V2.5 | 1269 |
| Gemini 3.1 Flash-Lite Preview | 1269 |
| Qwen3.5 122B A10B | 1261 |
| MiMo-V2-Omni | 1253 |
| GPT-4.1 (2025-04-14) | 1246 |
| Gemini 2.5 Flash | 1245 |
| Grok 4.3 | 1243 |
| Qwen3 VL 235B A22B Thinking | 1235 |