Arena Vision — Diagram (Style Controlled)
Multimodal
Style-controlled Vision Arena rating for diagram-understanding 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 | 1353 |
| Gemini 3.8 Flash | 1333 |
| Opus 4.7 | 1333 |
| Opus 4.6 | 1331 |
| Claude Opus 5 | 1329 |
| Claude Fable 5.1 | 1323 |
| GPT-5.5 | 1323 |
| Qwen3.8-Max | 1323 |
| Muse Spark 1.3 | 1322 |
| Claude Sonnet 5.5 | 1321 |
| GPT-5.4 | 1321 |
| Gemini 3.7 Flash | 1320 |
| GPT-6.1 Sol | 1319 |
| Opus 4.8 | 1319 |
| GPT-5.6 Sol | 1318 |
| Muse Spark 1.2 | 1316 |
| Gemini 3.5 Flash | 1313 |
| Muse Spark | 1312 |
| Gemini 3.6 Flash | 1310 |
| GPT-6 Astra | 1310 |
| Gemini 3.1 Pro Preview | 1308 |
| GLM-5.3 Flash | 1306 |
| Grok 4.5 | 1306 |
| Sonnet 4.6 | 1306 |
| Muse Spark 1.1 | 1305 |
| Gemini 3 Pro Preview | 1301 |
| Step 5 Preview | 1301 |
| GPT-5.6 Terra | 1299 |
| Grok 4.6 | 1294 |
| DeepSeek V4.1 Flash | 1293 |
| Sonnet 5 | 1293 |
| Kimi K2.6 | 1293 |
| Gemini 3 Flash Preview | 1293 |
| Gemini 3.5 Flash-Lite | 1292 |
| Qwen3.7-Plus (source unspecified) | 1290 |
| GPT-5.4 Mini | 1283 |
| Gemma 4 31B IT | 1283 |
| Grok 4.7 | 1280 |
| GPT-5.6 Luna | 1280 |
| Kimi K2.5 | 1280 |