Qwen3.6Open Weight
Qwen3.6 is an AI model released by Qwen on Thursday, Apr 16 2026, 14 days after Qwen3.6-Plus. It is an open-weight model — the trained weights are available to download and run. It is a 35B parameter model with a 256k token context window. Benchmark results (shown below) cover SWE-Bench Pro, SWE-Bench Verified, SWE-Bench Multilingual, Terminal-Bench 2.0, Humanity's Last Exam, GPQA Diamond, and 3 more.
Benchmarks
Agentic coding
SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
49.5%
#17 of 18Best: Claude Fable 5 · 80.3%
Coding
SWE-Bench VerifiedReal 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.
73.4%
#20 of 36Best: Claude Fable 5 · 95.5%
Multilingual coding
SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better.
67.2%
#9 of 10Best: Claude Opus 4.8 · 84.4%
Agentic terminal coding
Terminal-Bench 2.0Can 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.
51.5%
#11 of 13Best: GPT-5.5 · 82.7%
Multidisciplinary reasoning
Humanity's Last ExamHumanity'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.
21.4%
no tools
#14 of 14Best: Claude Opus 5 · 56.3%
Science
GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better.
86%
#24 of 46Best: GPT-5.4-Pro · 94.4%
Chart reasoning
CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better.
78%
#11 of 12Best: Muse Spark · 88.9%
Multimodal reasoning
MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better.
75.3%
#7 of 9Best: Gemini 3.5 Flash · 83.6%
Multimodal
MMMUTests the AI on understanding images and text together across many college subjects. Higher is better.
81.7%
#2 of 7Best: Qwen3.5 · 85%
Qwen3.6 — frequently asked questions
- When was Qwen3.6 released?
- Qwen3.6 was released by Qwen on Thursday, Apr 16 2026.
- Who made Qwen3.6?
- Qwen3.6 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 proprietary Max and Plus tier sold through Alibaba Cloud.
- What benchmark scores did Qwen3.6 get?
- Qwen3.6 reports 9 tracked benchmark scores — SWE-Bench Pro: 49.5%; SWE-Bench Verified: 73.4%; SWE-Bench Multilingual: 67.2%; Terminal-Bench 2.0: 51.5%; Humanity's Last Exam (no tools): 21.4%; GPQA Diamond: 86%; CharXiv Reasoning: 78%; MMMU-Pro: 75.3%; MMMU: 81.7%. Scores are the figures published at release by Qwen.
- What is the context window of Qwen3.6?
- Qwen3.6 has a context window of 256k. That is the maximum amount of input plus output the model can hold in a single request.
- How many parameters does Qwen3.6 have?
- Qwen3.6 is reported at 35B parameters.
- Is Qwen3.6 open source?
- Partly. Qwen3.6 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?
- Qwen's previous tracked release was Qwen3.6-Plus on Apr 2 2026, 14 days earlier. It was followed by Qwen3.7-Max on May 20 2026.