DataLearner logo
QW

Qwen3-Next

Chat modelQwen3

Qwen3-Next-80B-A3B

Release date: 2025-09-11Updated: 2025-09-14Views: 2,181
Parameters
80B
Context length
256K
Multilingual
Supported
Reasoning ability
3/5

Qwen3-Next-80B-A3B is an AI model published by Alibaba, released on 2025-09-11, for Chat model, with 80B parameters, and 256K context length, with a 90.30 score on GSM8K.

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

Qwen3-Next

Model basics

Reasoning traces
No data
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
256K tokens
Max output length
32K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-09-11
Model file size
No data
MoE architecture
Yes
Total params / Active params
80B / 3B
Knowledge cutoff
No data
Qwen3-Next

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
N/A
Qwen3-Next

Official resources

Paper
DataLearnerAI blog
Qwen3-Next

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.090/ 1M$1.10/ 1M

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Qwen3-Next

Benchmark Results

Qwen3-Next currently shows benchmark results led by GSM8K (15 / 70, score 90.30), MMLU (44 / 124, score 84.72), BBH (10 / 21, score 87.13). 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

6 evaluations
Benchmark / mode
Score
Rank/total
BBH
Standard Mode
87.13
10 / 21
MMLU
Standard Mode
84.72
44 / 124
MMLU Pro
Standard Mode
66.05
105 / 133
LiveBench
Standard Mode
48.35
99 / 115
LiveBench
Thinking Mode
50.41
90 / 115
GPQA
Standard Mode
43.43
12 / 16

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
90.30
15 / 70
AIME2025
Standard Mode
69.50
74 / 106
MATH
Standard Mode
62.36
28 / 42

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
56.60
81 / 127
Qwen3-Next

Publisher

Qwen3-Next-80B-A3B

Model Overview

Qwen3-Next-80B-A3B is an AI model published by Alibaba, released on 2025-09-11, for Chat model, with 80B parameters, and 256K context length, with a 90.30 score on GSM8K.

DataLearner on WeChat

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

DataLearner WeChat QR code