qwen/qwen3.6-max-previewQwen 3.6 Max (Preview) is Alibaba’s AI model, released Apr 20, 2026. It scores 150 on the Epoch Capabilities Index, costs $1.04/M input and $6.24/M output tokens, and handles a 262K-token context window. Its strongest use case is agentic & tools, where it ranks in the 85th percentile of the models Model Beat tracks.
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters.
Scores on standardized evaluations. Higher is better — and rank shows where Qwen 3.6 Max (Preview) lands among all models tracked on Model Beat.
Graduate-level scientific reasoning
Frontier of human expert knowledge
Common-sense trick questions
Factual accuracy & hallucination
Scientific research coding
Real GitHub issue resolution
Human-rated web development
Olympiad-qualifier math
Research-level math problems
Hardest research math
Tool-agent-user reliability
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters.
Qwen 3.6 Max (Preview) is an AI model developed by Alibaba, part of the Qwen family, released Apr 20, 2026.
Qwen 3.6 Max (Preview) is served from $1.04 per million input tokens and $6.24 per million output tokens (representative pricing via OpenRouter).
Qwen 3.6 Max (Preview) supports a context window of up to 262K tokens.
On standardized evaluations tracked by Epoch AI, Qwen 3.6 Max (Preview) scores 95.9% on τ²-bench, 52.0% on SimpleQA Verified, 76.7% on SWE-bench Verified.
Qwen 3.6 Max (Preview) is a proprietary model (Unknown), available through its provider's API rather than as a downloadable open-weight model.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Nov 12, 2026.