Qwen 3.6 Max: benchmark results
Alibaba's closed-weights Qwen 3.6 Max Preview flagship with a 256K context window. Provider: Alibaba. Released 2026-04-20. Access: API.
Unified ELO 1685 ± 1, rank #77 of 1392 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PerfCodeBench | 66.32 | CGRE (self-reported) | 94.7 |
| FORTIS | 51.3 | Task 1 EM (self-reported) | 88.9 |
| GroupTravelBench | 9.66 | GU (Group Utility) (self-reported) | 87.5 |
| LiveSQLBench | 33.79 | Success Rate (self-reported) | 84.4 |
| AIIQ Composite IQ | 114 | Composite IQ (self-reported) | 67.5 |
| PDP-Bench | 71.31 | Macro-F1 (self-reported) | 66.7 |
| Vending-Bench 2 | 4254.19 | Money Balance ($) | 49.4 |
| CHI-Bench | 16.4 | Overall Pass@1 (%) | 48 |
| DystopiaBench | 71.1 | Dystopian Compliance Score (0-100) | 26.8 |
| StartupBench | 59.46 | Score (%) | 12.5 |
| AgentCIBench | 97.4 | Leakage (self-reported) | 7.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-max · How It Works · Data refreshed daily, snapshot 2026-09-05.