# Qwen3.6-27B

Qwen3.6-27B is an AI model released by Qwen on Apr 22 2026. It has 27B parameters, a 256k context window and open weight. Tracked results include 87.8% on GPQA Diamond, 77.2% on SWE-Bench Verified and 83.9% on LiveCodeBench.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen3.6-27B |
| Developer | Qwen |
| Release date | Wednesday, Apr 22 2026 |
| Licensing | Open Weight |
| Parameters | 27B |
| Context window | 256k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| SWE-Bench Verified | 77.2% | Lab | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| SWE-Bench Multilingual | 71.3% | Lab | Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. |
| NL2Repo-Bench | 36.2% | 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. |
| LiveCodeBench | 83.9% | Lab | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |
| Terminal-Bench 2.0 | 59.3% | 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. |
| Humanity's Last Exam (no tools) | 24% | Lab | Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. |
| AIME 2026 | 94.1% | Lab | single-answer accuracy on the 2026 invitational mathematics exam without tools |
| GPQA Diamond | 87.8% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| MMLU-Pro | 86.2% | Lab | accuracy on the ten-option MMLU-Pro benchmark |
| CharXiv Reasoning | 78.4% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 75.8% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |
| MMMU | 82.9% | Lab | Tests the AI on understanding images and text together across many college subjects. Higher is better. |

## About Qwen3.6-27B

Qwen3.6-27B was released on April 22, 2026 as a dense open-weight alternative to the 35B-A3B mixture-of-experts model. It retained text and visual inputs and both thinking and non-thinking modes.

In Qwen's launch evaluation, the 27B checkpoint scored 77.2 on SWE-bench Verified and 59.3 on Terminal-Bench 2.0. The dense architecture gave developers a smaller total weight count with a different inference profile from the sparse model.

## Questions and answers

### When was Qwen3.6-27B released?

Qwen3.6-27B was released by Qwen on Wednesday, Apr 22 2026.

### Who made Qwen3.6-27B?

Qwen3.6-27B 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 Qwen3.6-27B get?

Qwen3.6-27B reports 12 tracked benchmark scores — SWE-Bench Verified: 77.2%; SWE-Bench Multilingual: 71.3%; NL2Repo-Bench: 36.2%; LiveCodeBench: 83.9%; Terminal-Bench 2.0: 59.3%; Humanity's Last Exam (no tools): 24%; AIME 2026: 94.1%; GPQA Diamond: 87.8%; MMLU-Pro: 86.2%; CharXiv Reasoning: 78.4%; MMMU-Pro: 75.8%; MMMU: 82.9%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Qwen3.6-27B?

Qwen3.6-27B has a context window of 256k. Providers may specify separate input and output token limits.

### How many parameters does Qwen3.6-27B have?

Qwen3.6-27B is reported at 27B parameters.

### Is Qwen3.6-27B open source?

Partly. Qwen3.6-27B is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Qwen3.6-27B?

Qwen's previous tracked release was Qwen3.6 on Apr 16 2026, 6 days earlier. It was followed by Qwen3.7-Max on May 20 2026.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen3.6-27b
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.
