DataLearner logo
QW

Qwen3-8B

Reasoning modelQwen3

Qwen3-8B

Release date: 2025-04-28Updated: 2026-07-17 23:18:30.0163,894
Live demoGitHubHugging FaceCompare
Parameters
8B
Context length
128K
Chinese support
Supported
Reasoning ability

Qwen3-8B is a reasoning model from Alibaba, released on 2025-04-28. It accepts text input and returns text output. The cataloged parameter count is 8B. The recorded context window is 128K, and the recorded maximum output is 126K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Apache 2.0 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

Qwen3-8B

Model basics

Reasoning traces
Supported
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
128K tokens
Max output length
126K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-04-28
Model file size
16GB
MoE architecture
No
Total params / Active params
8B / N/A
Knowledge cutoff
No data
Qwen3-8B

Open source & experience

Code license
Apache 2.0
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
https://github.com/QwenLM/Qwen3
Hugging Face
https://huggingface.co/Qwen/Qwen3-8B
Live demo
https://chat.qwen.ai/
Qwen3-8B

Official resources

Paper
No paper available
DataLearnerAI blog
DataLearnerAI blog
Qwen3-8B

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-¥0.0005/ 1K¥0.0020/ 1K
Qwen3-8B

Benchmark Results

Qwen3-8B currently shows benchmark results led by MATH-500 (11 / 44, score 97.40), GPQA (6 / 16, score 62), AIME 2024 (30 / 62, score 79.40). 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

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
72.50
90 / 133
GPQA
Standard Mode
62
6 / 16

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
39.30
210 / 224
GPQA Diamond
Thinking Mode
62
179 / 224

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
87.40
40 / 44
MATH-500
Thinking Mode
97.40
11 / 44
AIME 2024
Standard Mode
79.40
30 / 62
AIME 2024
Thinking Mode
76
35 / 62
AIME2025
Standard Mode
20.90
104 / 106
AIME2025
Thinking Mode
67.30
76 / 106

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
61.80
72 / 126
LiveCodeBench
Thinking Mode
57.50
76 / 126

Writing and Creative Capabilities

2 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
64.50
23 / 23
Creative Writing
Thinking Mode
75
21 / 23
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

Qwen3-8B

Publisher

Qwen3-8B

Model Overview

Qwen3-8B is a reasoning model from Alibaba, released on 2025-04-28.

It accepts text input and produces text output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 8B. The recorded context window is 128K, and the recorded maximum output is 126K.

The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. The page records 2 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment. The evaluation section contains 14 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.

Qwen3-8B

FAQ

What is Qwen3-8B?

Qwen3-8B is a reasoning model from Alibaba, released on 2025-04-28. It accepts text input and returns text output. The cataloged parameter count is 8B. The recorded context window is 128K, and the recorded maximum output is 126K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Apache 2.0 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 Qwen3-8B support?

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

What are the main recorded specifications for Qwen3-8B?

The cataloged parameter count is 8B. The recorded context window is 128K, and the recorded maximum output is 126K. Fields without a source-backed value remain undisclosed.

Does Qwen3-8B have API pricing?

The page records 2 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for Qwen3-8B?

The evaluation section contains 14 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Qwen3-8B open source?

The checkpoint is listed under the Apache 2.0 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