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

BenchmarkScoreMetricPercentile
Nejumi 4 - ALT Average91.81Score (%)100
Nejumi 4 - GLP - Expression99.5Score (%)100
PawBench - QwenPaw78.35Overall Score (%)100
AI for Education Pedagogy - Science94.54Accuracy (%)98.7
Nejumi 4 - GLP - Semantic Analysis86.1Score (%)97.5
Wolfram LLM Benchmarking Project68.7Correct Functionality (%)96.8
Nejumi 4 - ALT - Controllability93.37Score (%)96.7
Nejumi 4 - ALT - Toxicity87.13Score (%)96.7
AA TAU-2 Bench95.91Accuracy (%)96.2
AI for Education Pedagogy - Primary94.37Accuracy (%)96.2
AA IFBench76.6Accuracy (%)95.8
AI for Education Pedagogy89.66Accuracy (%)95.4

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