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

BenchmarkScoreMetricPercentile
PerfCodeBench66.32CGRE (self-reported)94.7
FORTIS51.3Task 1 EM (self-reported)88.9
GroupTravelBench9.66GU (Group Utility) (self-reported)87.5
LiveSQLBench33.79Success Rate (self-reported)84.4
AIIQ Composite IQ114Composite IQ (self-reported)67.5
PDP-Bench71.31Macro-F1 (self-reported)66.7
Vending-Bench 24254.19Money Balance ($)49.4
CHI-Bench16.4Overall Pass@1 (%)48
DystopiaBench71.1Dystopian Compliance Score (0-100)26.8
StartupBench59.46Score (%)12.5
AgentCIBench97.4Leakage (self-reported)7.1

Interactive version: theaggregate.ai/model?slug=qwen-3-6-max · How It Works · Data refreshed daily, snapshot 2026-09-05.