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
MMLU
67.6%自报
TruthfulQA
50.6%自报
BigCodeBench
41.0%自报
Language
MMLU-Base
68.0%自报
MMLU-Redux
66.6%自报
MMLU-Pro
40.1%自报
Math
GSM8k
83.9%自报
MATH
46.6%自报
TheoremQA
34.0%自报
STEM
34.0%自报
Reasoning
HumanEvalOpenAI (2021)
88.4%自报
MBPP
0.83 / 100自报
HellaSwagAI2 (2019)
76.8%自报
Winogrande
72.9%自报
ARC-C
60.9%自报
CRUXEval-Input-CoT
56.5%自报
CRUXEval-Output-CoT
56.0%自报
Aider
55.6%自报
LiveCodeBench
18.2%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))Language60
Math60
Reasoning60
General60
Legal50
Finance50
Healthcare50
Code50
Physics30
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