DataLearner logo
QW

Qwen3.6-27B

Reasoning modelCoding modelQwen3.6

Qwen3.6-27B

Release date: 2026-04-22Updated: 2026-08-23Views: 3,569
Live demoGitHubHugging FaceCompare
Parameters
27B
Context length
128K
Multilingual
Supported
Reasoning ability
3/5

Qwen3.6-27B is a reasoning model from Alibaba, released on 2026-04-22. It accepts text, image, and video input and returns text output. The cataloged parameter count is 27B. The recorded context window is 128K, and the recorded maximum output is 16K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Qwen License, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen3.6-27B

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
128K tokens
Max output length
16K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image, Video → Text
Release date
2026-04-22
Model file size
No data
MoE architecture
No
Total params / Active params
27B / Not applicable
Knowledge cutoff
No data
Qwen3.6-27B

Open source & experience

Code license
Qwen License
Weights license
Qwen License- Commercial use permitted
GitHub repo
N/A
Hugging Face
huggingface.co/Qwen/Qwen3.6-27B
Live demo
qwen.ai
Qwen3.6-27B

Official resources

Paper
Paper
DataLearnerAI blog
DataLearnerAI blog
Qwen3.6-27B

API details

API speed
3/5
No public API pricing yet.
Qwen3.6-27B

Benchmark Results

Qwen3.6-27B currently shows benchmark results led by C-Eval (5 / 48, score 91.40), MMLU Pro (19 / 176, score 86.20), LiveCodeBench (35 / 250, score 83.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

8 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Thinking Mode
91.40
5 / 48
MMLU Pro
Thinking Mode
86.20
19 / 176
LiveBench
Standard Mode
64.03
54 / 117
HLE
Standard Mode
15.10
333 / 563
HLE
Thinking Mode
24
259 / 563
HLE
Thinking Mode
23.10
265 / 563
CritPt
Standard Mode
0.90
158 / 200
CritPt
Thinking Mode
1.10
147 / 200

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
84.85
159 / 462
GPQA Diamond
Thinking Mode
87.80
123 / 462

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
83.90
35 / 250
SWE-bench Verified
Thinking ModeTools
77.20
28 / 116
SWE-bench Multilingual
Thinking ModeTools
71.30
21 / 30
SWE-Bench Pro - Public
Thinking ModeTools
53.50
39 / 62
SciCode
Thinking Mode
42.80
96 / 130

Agent Level Benchmark

6 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Standard ModeTools
93.60
46 / 264
τ²-Bench - Telecom
Thinking ModeTools
94.20
38 / 264
Terminal Bench Hard
Standard ModeTools
21.20
145 / 244
Terminal Bench Hard
Thinking ModeTools
34.80
75 / 244
τ³-Banking
Standard ModeTools
9.30
134 / 164
τ³-Banking
Thinking ModeTools
16.70
100 / 164

Instruction Following

2 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Standard Mode
45.70
177 / 282
IF Bench
Thinking Mode
67.60
88 / 282

AI Agent - Tool Usage

3 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench 2.1
Standard ModeTools
51.30
129 / 192
Terminal-Bench 2.1
Thinking ModeTools
60.70
110 / 192
Terminal Bench 2.0
Thinking ModeTools
59.30
20 / 48

Text Embedding

2 evaluations
Benchmark / mode
Score
Rank/total
Context Arena
Standard Mode
53.78
82 / 126
Context Arena
Thinking Mode
82.17
32 / 126

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
AIME 2026
Thinking Mode
94.10
15 / 29
IMO-AnswerBench
Thinking Mode
80.80
20 / 24
FrontierMath v2
Standard Mode
34.04
41 / 58

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
Standard Mode
66.70
118 / 170

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
72.40
27 / 29

Productivity Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
Standard ModeTools
1043
87 / 105
Harvey Lab-AA
Thinking ModeTools
82.30
27 / 43

Multimodal Understanding

3 evaluations
Benchmark / mode
Score
Rank/total
MMMU-Pro
Standard Mode
71.70
118 / 227
MMMU-Pro
Thinking Mode
74.60
91 / 227
GDP.pdf
Thinking Mode
11
76 / 118
View benchmark analysisCompare with other models

Compare with other models

Qwen3.6-27B

Publisher

Qwen3.6-27B

Model Overview

Qwen3.6-27B is a reasoning model from Alibaba, released on 2026-04-22.

It accepts text, image, and video input and produces text output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 27B. The recorded context window is 128K, and the recorded maximum output is 16K.

The checkpoint is listed under the Qwen License, with the license link included in the model references. The evaluation section contains 13 cataloged benchmark results with their recorded modes and scores. The page links 4 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Qwen3.6-27B

FAQ

What is Qwen3.6-27B?

Qwen3.6-27B is a reasoning model from Alibaba, released on 2026-04-22. It accepts text, image, and video input and returns text output. The cataloged parameter count is 27B. The recorded context window is 128K, and the recorded maximum output is 16K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Qwen License, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Qwen3.6-27B support?

The current model record lists text, image, and video as input and text as output.

What are the main recorded specifications for Qwen3.6-27B?

The cataloged parameter count is 27B. The recorded context window is 128K, and the recorded maximum output is 16K. Fields without a source-backed value remain undisclosed.

Why is no API price shown for Qwen3.6-27B?

Open-weight checkpoint; no first-party hosted price published for this exact checkpoint.

Are benchmark results available for Qwen3.6-27B?

The evaluation section contains 13 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Qwen3.6-27B open source?

The checkpoint is listed under the Qwen License, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code