DataLearner logo
QW

Qwen3-Coder-Next

Coding modelQwen3

Qwen3-Coder-Next

Release date: 2026-02-03Updated: 2026-07-17 21:57:49.7012,711
Live demoGitHubHugging FaceCompare
Parameters
8B
Context length
256K
Chinese support
Supported
Reasoning ability

Qwen3-Coder-Next is a coding model from Alibaba, released on 2026-02-03. It accepts text input and returns text output. The cataloged parameter count is 8B, with 300M active parameters per inference. The recorded context window is 256K, and the recorded maximum output is 64K. Cataloged capabilities include Multilingual and Coding model. 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-Coder-Next

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking Level · Extended (Default)Standard Mode
Context length
256K tokens
Max output length
64K tokens
Model type
Coding model
Modality (in / out)
Text → Text
Release date
2026-02-03
Model file size
48GB
MoE architecture
Yes
Total params / Active params
8B / 300M
Knowledge cutoff
No data
Qwen3-Coder-Next

Open source & experience

Code license
Qwen License
Weights license
Qwen License- Commercial use permitted
GitHub repo
https://github.com/QwenLM/Qwen3-Coder
Hugging Face
https://huggingface.co/Qwen/Qwen3-Coder-Next
Live demo
No live demo
Qwen3-Coder-Next

Official resources

Paper
Paper
DataLearnerAI blog
No blog post yet
Qwen3-Coder-Next

API details

API speed
5/5
No public API pricing yet.
Qwen3-Coder-Next

Benchmark Results

Qwen3-Coder-Next currently shows benchmark results led by SWE-bench Verified (58 / 113, score 70.60), Pinch Bench (25 / 37, score 79.10), Claw Bench (24 / 29, score 75.80). 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

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench 2.0
36.20
46 / 47

Claw-style Agent Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
79.10
25 / 37
Claw Bench
Thinking ModeTools
75.80
24 / 29
View benchmark analysisCompare with other models

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Qwen3-Coder-Next

Publisher

Qwen3-Coder-Next

Model Overview

Qwen3-Coder-Next is a coding model from Alibaba, released on 2026-02-03.

It accepts text input and produces text output. Its cataloged capabilities include Multilingual and Coding model. The cataloged parameter count is 8B, with 300M active parameters per inference. The recorded context window is 256K, and the recorded maximum output is 64K.

The checkpoint is listed under the Qwen License, with the license link included in the model references. The evaluation section contains 5 cataloged benchmark results with their recorded modes and scores. The page links 3 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-Coder-Next

FAQ

What is Qwen3-Coder-Next?

Qwen3-Coder-Next is a coding model from Alibaba, released on 2026-02-03. It accepts text input and returns text output. The cataloged parameter count is 8B, with 300M active parameters per inference. The recorded context window is 256K, and the recorded maximum output is 64K. Cataloged capabilities include Multilingual and Coding model. 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-Coder-Next support?

The current model record lists text as input and text as output.

What are the main recorded specifications for Qwen3-Coder-Next?

The cataloged parameter count is 8B, with 300M active parameters per inference. The recorded context window is 256K, and the recorded maximum output is 64K. Fields without a source-backed value remain undisclosed.

Why is no API price shown for Qwen3-Coder-Next?

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

Are benchmark results available for Qwen3-Coder-Next?

The evaluation section contains 5 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Qwen3-Coder-Next 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