Chatbot Arena (Vision - Chinese): leaderboard
The arena.ai vision board restricted to image battles whose prompt is in Chinese. Each battle pairs an uploaded image and a prompt with two anonymous model answers, and the voter picks the better one. The rating is refit over the conversations in this category alone, so the order can differ from the overall vision table, and higher is better.
Metric: Arena Score. Source: arena.ai. 125 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.8 Flash (High) | 1380 | #21 (Gemini 3.8 Flash) |
| 2 | Gemini 3.7 Flash (High) | 1367 | #23 (Gemini 3.7 Flash) |
| 3 | Claude Opus 5 (High) | 1367 | #12 (Claude Opus 5) |
| 4 | Muse Spark 1.3 (xHigh) | 1361 | #24 (Muse Spark 1.3) |
| 5 | GPT-6 Astra (Max) | 1357 | #6 (GPT-6 Astra) |
| 6 | Claude Fable 5 (High) | 1355 | #16 (Claude Fable 5) |
| 7 | Qwen 3.8 Max | 1353 | #35 |
| 8 | Claude Opus 4.6 (High) | 1352 | #63 (Claude Opus 4.6) |
| 9 | Claude Opus 4.6 | 1348 | #63 |
| 10 | Gemini 3.5 Flash (High) | 1348 | #60 (Gemini 3.5 Flash) |
| 11 | Claude Opus 4.7 | 1346 | #49 |
| 12 | Gemini 3.5 Flash (Medium) | 1345 | #60 (Gemini 3.5 Flash) |
| 13 | GLM-5.3 Flash | 1343 | #65 |
| 14 | Gemini 3 Pro | 1342 | #80 |
| 15 | Muse Spark 1.3 (Max) | 1342 | #24 (Muse Spark 1.3) |
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-vision-chinese · How It Works · Data refreshed daily, snapshot 2026-10-20.