跳转到主要内容

Qwen2.5 Coder Instruct 7B

AlibabaQwen开源权重Apache 2.0 · 商用许可

描述

Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, and repair while maintaining strong performance in math and general tasks. The model demonstrates exceptional capabilities in multi-programming language tasks and code reasoning.

发布日期
2024-09-19
参数规模
7.0B
上下文长度
—
支持模态
—

能力雷达图

60
general
50
coding
60
reasoning
26
science估算
57
agents
0
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU67.6%自报
TruthfulQA50.6%自报
BigCodeBench41.0%自报

Language

MMLU-Base68.0%自报
MMLU-Redux66.6%自报
MMLU-Pro40.1%自报

Math

GSM8k83.9%自报
MATH46.6%自报
TheoremQA34.0%自报
STEM34.0%自报

Reasoning

HumanEvalOpenAI (2021)88.4%自报
MBPP0.83 / 100自报
HellaSwagAI2 (2019)76.8%自报
Winogrande72.9%自报
ARC-C60.9%自报
CRUXEval-Input-CoT56.5%自报
CRUXEval-Output-CoT56.0%自报
Aider55.6%自报
LiveCodeBench18.2%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Language
60
Math
60
Reasoning
60
General
60
Legal
50
Finance
50
Healthcare
50
Code
50
Physics
30

定价

暂无定价数据

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接