AIbase
EN
Home
AI Models Finder
Qwen2.5 Instruct 72B
Q

Qwen2.5 Instruct 72B

Qwen2.5-72B-Instruct is a language model with 72 billion parameters that has undergone instruction fine-tuning and belongs to the Qwen2.5 series. It is designed to follow instructions, generate long texts (over 8K tokens), understand structured data (such as tables), and generate structured outputs, especially JSON. This model supports more than 29 languages.
Intelligence(Relatively Weak)
Speed(Relatively Slow)
Input Supported Modalities
No
Is Reasoning Model
131,072
Context Window
8,192
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

￥2.52 /M tokens
Input
￥2.88 /M tokens
Output
- /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo
Qwen Turbo
Wan2.2

Basic Parameters

Qwen2.5 Instruct 72BTechnical Parameters
Parameter Count
72,700.0M
Context Length
131.07k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
100
Release Date
2024-09-19
Response Speed
58.21,355 tokens/s

Benchmark Scores

Below is the performance of Qwen2.5 Instruct 72B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
40.41
Large Language Model Intelligence Level
Coding Index
27.18
Indicator of AI model performance on coding tasks
Math Index
50.9
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
72
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
49.1
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.2
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
27.6
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
26.7
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
88.3
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
85.8
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
16
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase