Chatbot Arena (Vision - Homework): leaderboard
arena.ai’s vision leaderboard restricted to battles that ask for help with homework-style questions about an image, such as worked problems, diagrams or worksheets. Same crowd-vote Arena Score as the headline vision board, refitted over that category’s votes alone.
Metric: Arena Score. Source: arena.ai. 116 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol (Max) | 1355 | #7 (GPT-6.1 Sol) |
| 2 | Claude Fable 5 (High) | 1348 | #20 (Claude Fable 5) |
| 3 | Claude Opus 5.5 (High) | 1348 | #3 (Claude Opus 5.5) |
| 4 | GPT-6 Astra (Max) | 1346 | #6 (GPT-6 Astra) |
| 5 | Qwen 3.8 Max | 1341 | #34 |
| 6 | Gemini 3.8 Flash (High) | 1337 | #30 (Gemini 3.8 Flash) |
| 7 | GPT-5.5 (High) | 1336 | #33 (GPT-5.5) |
| 8 | Claude Fable 5.1 (Max) | 1335 | #10 (Claude Fable 5.1) |
| 9 | GPT-5.5 | 1332 | #33 |
| 10 | Claude Opus 4.8 (High) | 1332 | #39 (Claude Opus 4.8) |
| 11 | GPT-5.4 (High) | 1331 | #83 (GPT-5.4) |
| 12 | Claude Opus 4.7 (High) | 1331 | #51 (Claude Opus 4.7) |
| 13 | Claude Opus 5 (High) | 1328 | #16 (Claude Opus 5) |
| 14 | GPT-5.6 Terra (xHigh) | 1327 | #40 (GPT-5.6 Terra) |
| 15 | Claude Opus 4.7 | 1324 | #51 |
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-vision-homework · How It Works · Data refreshed daily, snapshot 2026-11-05.