DataLearner logo
QW

Qwen3 Max (Preview)

Chat modelQwen3

Qwen3 Max (Preview)

Release date: 2025-09-05Updated: 2026-01-27Views: 1,867
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
256K
Multilingual
Supported
Reasoning ability
4/5

Qwen3 Max (Preview) is an AI model published by Alibaba, released on 2025-09-05, for Chat model, and 256K context length, with a 84.20 score on τ²-Bench - Telecom.

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

Qwen3 Max (Preview)

Model basics

Reasoning traces
Supported
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
2025-09-05
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
Qwen3 Max (Preview)

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
Qwen3 Max (Preview)

Official resources

Paper
N/A
DataLearnerAI blog
N/A
Qwen3 Max (Preview)

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥0.0032/ 1K tokens¥0.013/ 1K tokens
TextContext > 32768¥0.0064/ 1K tokens¥0.026/ 1K tokens
Batch
TypeConditionInputOutput
Text-¥0.0016/ 1K tokens¥0.0064/ 1K tokens
international
TypeConditionInputOutput
TextContext <= 32000$1.20/ 1M tokens$6.00/ 1M tokens
TextContext > 32000, Context <= 128000$2.40/ 1M tokens$12.00/ 1M tokens
TextContext > 128000, Context <= 256000$3.00/ 1M tokens$15.00/ 1M tokens

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

Qwen3 Max (Preview)

Benchmark Results

Qwen3 Max (Preview) currently shows benchmark results led by MMLU Pro (40 / 176, score 84), τ²-Bench - Telecom (96 / 264, score 84.20), AIME2025 (97 / 215, score 80.60). 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

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
84
40 / 176
HLE
Standard Mode
11.10
376 / 563

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
76
272 / 462

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Standard Mode
69.60
63 / 116
LiveCodeBench
Standard Mode
57.50
139 / 250

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Standard Mode
80.60
97 / 215

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
Standard ModeTools
19
32 / 35

Agent Level Benchmark

3 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Thinking ModeTools
84.20
96 / 264
τ²-Bench
Standard ModeTools
74
23 / 44
τ²-Bench
Thinking ModeTools
72
25 / 44
Qwen3 Max (Preview)

Publisher

Qwen3 Max (Preview)

Model Overview

Qwen3 Max (Preview) is an AI model published by Alibaba, released on 2025-09-05, for Chat model, and 256K context length, with a 84.20 score on τ²-Bench - Telecom.

DataLearner on WeChat

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

DataLearner WeChat QR code