Qwen3.6 Max Preview Benchmark Update
Quality: 40/100 | Price: $2.925/M tokens | Output: 46.407 tok/s | HumanEval: 0.469%
View sourceQwen
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. It is optimized for agentic coding, tool use, and...
Running this yourself: can likely run on your own machine.
---
Quality Score
---
Arena ELO
Unknown
Parameters
262K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Apr 2026
Released
Benchmarks
19
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 40/100 | Price: $2.925/M tokens | Output: 46.407 tok/s | HumanEval: 0.469%
View sourceQuality: 40/100 | Price: $2.925/M tokens | Output: 46.407 tok/s | HumanEval: 0.469%
Quality: 40/100 | Price: $2.925/M tokens | Output: 46.937 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 47.021 tok/s | HumanEval: 0.469%
View sourceQuality: 51.8/100 | Price: $2.925/M tokens | Output: 45.755 tok/s | HumanEval: 0.469%
View sourceQuality: 51.8/100 | Price: $2.925/M tokens | Output: 39.966 tok/s | HumanEval: 0.469%
View sourceQuality: 40/100 | Price: $2.925/M tokens | Output: 46.937 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 47.021 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 45.755 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 39.966 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 38.701 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 38.156 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 37.661 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 38.521 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 40.546 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 41.317 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 41.454 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 40.694 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 40.996 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 40.345 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 39.966 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 39.497 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 38.034 tok/s | HumanEval: 0.469%
Quality: 51.8/100 | Price: $2.925/M tokens | Output: 37.364 tok/s | HumanEval: 0.469%
Qwen3.6 Max Preview is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.