Qwen 3.6 Max Preview: benchmark results
Alibaba's preview of the Qwen 3.6 Max flagship tier. Provider: Alibaba. Released 2026-04-20. Access: API.
Unified ELO 1703 ± 1, rank #52 of 1392 rated models, from 139 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Nejumi 4 - ALT Average | 91.81 | Score (%) | 100 |
| Nejumi 4 - GLP - Expression | 99.5 | Score (%) | 100 |
| PawBench - QwenPaw | 78.35 | Overall Score (%) | 100 |
| AI for Education Pedagogy - Science | 94.54 | Accuracy (%) | 98.7 |
| Nejumi 4 - GLP - Semantic Analysis | 86.1 | Score (%) | 97.5 |
| Wolfram LLM Benchmarking Project | 68.7 | Correct Functionality (%) | 96.8 |
| Nejumi 4 - ALT - Controllability | 93.37 | Score (%) | 96.7 |
| Nejumi 4 - ALT - Toxicity | 87.13 | Score (%) | 96.7 |
| AA TAU-2 Bench | 95.91 | Accuracy (%) | 96.2 |
| AI for Education Pedagogy - Primary | 94.37 | Accuracy (%) | 96.2 |
| AA IFBench | 76.6 | Accuracy (%) | 95.8 |
| AI for Education Pedagogy | 89.66 | Accuracy (%) | 95.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-max-preview · How It Works · Data refreshed daily, snapshot 2026-09-05.