Qwen 3.8 Max (Preview): benchmark results
Provider: Alibaba. Released 2026-08-03. Access: API.
Aggregate Rating 1817 ± 25, rank #68 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Design Arena (UI Components) | 1333 | Elo | 92.3 |
| Design Arena (3D) | 1330 | Elo | 88.6 |
| Design Arena (Game Dev) | 1311 | Elo | 87.4 |
| OpenHarmony Bench - New Features | 59.38 | Mean Task Completion (%) | 85.7 |
| OpenHarmony Bench - Specification Tasks | 34 | Mean Task Completion (%) | 85.7 |
| Design Arena (Data Viz) | 1283 | Elo | 85 |
| Design Arena (Website) | 1272 | Elo | 80.7 |
| FoodTruckBench | 44442.9 | Source-selected End Net Worth ($) | 79.7 |
| E-Commerce Bench | 416 | Final Assets (¥k, mean of 5 episodes) | 75 |
| OpenHarmony Bench | 55.99 | Mean Task Completion (%) | 71.4 |
| Design Arena (ASCII Art) | 1191 | Elo | 63.3 |
| OpenHarmony Bench - Bug Fixes | 69.95 | Mean Task Completion (%) | 57.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-max-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.