Qwen 3.6 Max (Preview) (Thinking): benchmark results

Provider: Alibaba. Released 2026-04-20. Access: API.

Unified ELO 1671 ± 1, rank #198 of 1919 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SuperCLUE-Writing - Content Quality86.67Score84.6
LLM2014 Logic 2026-0460.68Median Score82.5
SuperCLUE-Writing - Content Style89.45Score76.9
SuperCLUE-Writing - Constrained Writing92.51Score61.5
SuperCLUE-Writing - Mainstream Genre Writing81.73Score61.5
SuperCLUE-Writing - Overall86.47Score61.5
SuperCLUE-Writing - Content Creativity81.97Score7.7

Interactive version: theaggregate.ai/model?slug=qwen-3-6-max-preview-thinking · How It Works · Data refreshed daily, snapshot 2026-09-08.