跳转到主要内容

Qwen2.5 Instruct 72B

AlibabaQwenOpen WeightQwen · Commercial OK

描述

Qwen2.5-72B-Instruct is an instruction-tuned 72 billion parameter language model, part of the Qwen2.5 series. It is designed to follow instructions, generate long texts (over 8K tokens), understand structured data (e.g., tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities across over 29 languages.

发布日期
2024-09-19
参数规模
72.7B
上下文长度
33K
支持模态
text

能力雷达图

31
general
19
coding
29
reasoning
32
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

领域#排名分数来源
代码能力榜334
21.0
AA
通用能力榜285
38.0
AA
数学推理270
29.0
AA
科学能力332
33.0
AA

基准测试分数 (LLM Stats)

Biology

GPQA49.0%自报

Code

HumanEval86.6%自报
LiveCodeBench55.5%自报

Communication

MT-Bench0.94 / 100自报

Creativity

AlignBench81.6%自报
Arena Hard81.2%自报

Finance

MMLU-Pro71.1%自报

General

MBPP0.88 / 100自报
MMLU-Redux86.8%自报
IFEval84.1%自报
MultiPL-E75.1%自报
LiveBench52.3%自报

Math

GSM8k95.8%自报
MATH83.1%自报

AA 评测指数

Intelligence Index
15.6
Math Index
14.0
Coding Index
11.9
Math 500
0.9
Mmlu Pro
0.7
Gpqa
0.5
Ifbench
0.4
Tau2
0.3
Livecodebench
0.3
Scicode
0.3
Lcr
0.2
Aime
0.2
Aime 25
0.1
Terminalbench Hard
0.0
Hle
0.0

LLM Stats 分类评分

Communication
90
Creativity
90
Roleplay
90
Structured Output
80
Writing
80
Instruction Following
80
Language
80
Math
80
Reasoning
80
Code
70
Finance
70
General
70
Healthcare
70
Legal
70
Biology
50
Chemistry
50
Physics
50

定价

输入价格$0.36 / 1M tokens
输出价格$0.4 / 1M tokens
混合价格(3:1)$0.37 / 1M tokens

速度

Tokens/秒54.7 tokens/s
首Token延迟1.08s
首回答延迟1.08s

可用提供商

(LS 内部计价单位)

暂无提供商数据

外部链接