Qwen 3.8 Max: benchmark results
Provider: Alibaba. Released 2026-08-03. Access: API.
Unified ELO 1970 ± 7, rank #26 of 2656 rated models, from 380 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| KernelBench Hub - Hard | 69.26 | Best % of Hardware Roofline | 100 |
| LLM Stats (AndroidWorld) | 85.3 | Score (%) | 100 |
| LLM Stats (CoWorkBench) | 74.8 | Score (%) | 100 |
| LLM Stats (ERQA) | 77.8 | Score (%) | 100 |
| LLM Stats (HealthBench) | 60.2 | Score (%) | 100 |
| LLM Stats (LongBench v2) | 66.3 | Score (%) | 100 |
| LLM Stats (SkillsBench) | 70.2 | Score (%) | 100 |
| LLM Stats (VideoMME w sub.) | 90.4 | Score (%) | 100 |
| LLM Stats (Vision2Web) | 69 | Score (%) | 100 |
| MobilePA-Bench - Memory Usage | 64.63 | End-to-end success (%) | 100 |
| PLawBench | 73.2 | Overall (self-reported) | 100 |
| Qwen3.8 Launch - Dense200 | 87 | Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-max · How It Works · Data refreshed daily, snapshot 2026-09-19.