DataLearner logo
QW

Qwen2.5-Max

Chat modelQwen2.5

Qwen2.5-Max

Release date: 2025-01-28Updated: 2025-02-05Views: 1,096
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
128K
Multilingual
Supported
Reasoning ability
No data

Qwen2.5-Max is an AI model published by Alibaba, released on 2025-01-28, for Chat model, and 128K context length, requiring about 0 storage, with a 94.50 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

Qwen2.5-Max

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
No data
Release date
2025-01-28
Model file size
0
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
Qwen2.5-Max

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Qwen2.5-Max

Official resources

Paper
DataLearnerAI blog
N/A
Qwen2.5-Max

API details

API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥0.0024/ 1K tokens¥0.0096/ 1K tokens
Batch
TypeConditionInputOutput
Text-¥0.0012/ 1K tokens¥0.0048/ 1K tokens

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

Qwen2.5-Max

Benchmark Results

Qwen2.5-Max currently shows benchmark results led by GSM8K (9 / 70, score 94.50), MMLU (22 / 124, score 87.90), MBPP (19 / 96, 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

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
87.90
22 / 124
MMLU Pro
Standard Mode
76.10
82 / 176
HLE
Standard Mode
3.80
533 / 563

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
94.50
9 / 70
MATH
Standard Mode
68.50
24 / 42
FrontierMath
Standard Mode
1
52 / 60

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
80.60
19 / 96
HumanEval
Standard Mode
73.20
51 / 140
LiveCodeBench
Standard Mode
35.90
194 / 250

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
58.70
384 / 462

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
21.80
48 / 59
Qwen2.5-Max

Publisher

Qwen2.5-Max

Model Overview

Qwen2.5-Max is an AI model published by Alibaba, released on 2025-01-28, for Chat model, and 128K context length, requiring about 0 storage, with a 94.50 score on GSM8K.

DataLearner on WeChat

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

DataLearner WeChat QR code