Qwen2.5 Coder Instruct 7B
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
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
33K
支持模态
text
能力雷达图
20
general
13
coding
29
reasoning
21
science估算
0
agents
0
multimodal
Science 在缺少专门科学评测时使用推理能力代理估算。
排行榜排名
基准测试分数 (LLM Stats)
Code
HumanEval
88.4%自报
Aider
55.6%自报
LiveCodeBench
18.2%自报
Finance
MMLU-Base
68.0%自报
MMLU
67.6%自报
TruthfulQA
50.6%自报
MMLU-Pro
40.1%自报
TheoremQA
34.0%自报
General
MBPP
0.83 / 100自报
MMLU-Redux
66.6%自报
ARC-C
60.9%自报
BigCodeBench
41.0%自报
Language
Winogrande
72.9%自报
Math
GSM8k
83.9%自报
MATH
46.6%自报
STEM
34.0%自报
Reasoning
HellaSwag
76.8%自报
CRUXEval-Input-CoT
56.5%自报
CRUXEval-Output-CoT
56.0%自报
AA 评测指数
Intelligence Index10.0
Math 5000.7
Mmlu Pro0.5
Gpqa0.3
Scicode0.1
Livecodebench0.1
Aime0.1
Hle0.0
LLM Stats 分类评分
General60
Language60
Math60
Reasoning60
Code50
Finance50
Healthcare50
Legal50
Physics30
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒0.0 tokens/s
首Token延迟0.00s
首回答延迟0.00s
可用提供商
(LS 内部计价单位)暂无提供商数据