# Qwen3.6-Max-Preview

Qwen3.6-Max-Preview is an AI model released by Qwen on Apr 14 2026. It has a 256k context window. Tracked results include 42.9% on NL2Repo-Bench and 65.4% on Terminal-Bench 2.0.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen3.6-Max-Preview |
| Developer | Qwen |
| Release date | Tuesday, Apr 14 2026 |
| Licensing | Closed |
| Context window | 256k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| NL2Repo-Bench | 42.9% | Lab | Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. |
| Terminal-Bench 2.0 | 65.4% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. |

## About Qwen3.6-Max-Preview

Alibaba Cloud listed Qwen3.6-Max-Preview on April 14, 2026 as a hosted text-only preview. Qwen's April 18 write-up presented it as an upgrade over Qwen3.6-Plus for coding agents, instruction following and less common factual questions.

The preview scored 65.4 on Terminal-Bench 2.0 and 42.9 on NL2Repo in the launch chart. It was a separate preview checkpoint before the Qwen3.7 generation.

## Questions and answers

### When was Qwen3.6-Max-Preview released?

Qwen3.6-Max-Preview was released by Qwen on Tuesday, Apr 14 2026.

### Who made Qwen3.6-Max-Preview?

Qwen3.6-Max-Preview was built by Qwen. Alibaba's AI lab, building the Qwen family. The most prolific publisher of open-weight models of any major lab, alongside a closed Max and Plus tier sold through Alibaba Cloud.

### What benchmark scores did Qwen3.6-Max-Preview get?

Qwen3.6-Max-Preview reports 2 tracked benchmark scores — NL2Repo-Bench: 42.9%; Terminal-Bench 2.0: 65.4%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Qwen3.6-Max-Preview?

Qwen3.6-Max-Preview has a context window of 256k. Providers may specify separate input and output token limits.

### Is Qwen3.6-Max-Preview open source?

No. Qwen3.6-Max-Preview is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after Qwen3.6-Max-Preview?

Qwen's previous tracked release was Qwen3.6-Plus on Apr 2 2026, 12 days earlier. It was followed by Qwen3.6 on Apr 16 2026.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen3.6-max-preview
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
