Qwen: Qwen2.5 Coder 7B Instruct

Qwen: Qwen2.5 Coder 7B Instruct

qwen · Released Apr 15, 2025 Emerging
29.9
Our Score

Performance Profile

Intelligence2.2Technical0Value7.8Content2.5
Intelligence 2.2/10
Technical 0/10
Content 2.5/10
Value 7.8/10

Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE,..

$0.03 / 1M
Input Price
$0.09 / 1M
Output Price
32,768 tokens
Context Window
7B Parameters

Architecture

ModalityText → Text
TokenizerQwen
Parameters7B

Performance Indices

Source: Artificial Analysis

10 Intelligence Index

Benchmark Scores

Intelligence

GPQA Diamond 33.9% Graduate-level scientific reasoning
HLE 4.8% Humanity's Last Exam
MMLU Pro 47.3% Multi-task language understanding
MATH 500 66% Mathematical problem-solving
AIME 5.3% Competition mathematics
SciCode 14.8% Scientific computing

Technical

LiveCodeBench 12.6% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Qwen: Qwen2.5 Coder 7B Instruct stack up?

Compare side-by-side with other emerging models.

Compare Models

Model Information

OpenRouter ID qwen/qwen2.5-coder-7b-instruct
Providerqwen
Release Date April 15, 2025
Context Length32,768 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.03 $0.000030
Output $0.09 $0.000090