跳转到主要内容

Qwen2.5 Instruct 72B

AlibabaQwen开源权重Qwen · 商用许可

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
131K
支持模态
text

能力雷达图

28
general
27
coding
29
reasoning
32
science估算
28
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362
21.0
AA
通用能力榜305
36.0
AA
数学推理270
29.0
AA
科学能力357
32.0
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

Math Index
14.0
Intelligence Index
9.6
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

Roleplay
90
Communication
90
Creativity
90
Math
80
Reasoning
80
Structured Output
80
Instruction Following
80
Language
80
Writing
80
Legal
70
Finance
70
General
70
Healthcare
70
Code
70
Physics
50
Biology
50
Chemistry
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0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

11 个供应商

最便宜: Cortecs最贵: SiliconFlow
供应商输入输出
1Cortecs最便宜
$0.062
$0.231
2Abacus
$0.11
$0.38
3Kilo Gateway
$0.12
$0.39
4Chutes
$0.2989
$1.1957
5NanoGPT
$0.357
$0.408
6Alibaba主要
$0.36
$0.4
7OpenRouter
$0.36
$0.4
8NovitaAI
$0.38
$0.4
9Alibaba (China)
$0.574
$1.721
10SiliconFlow (China)
$0.59
$0.59
11SiliconFlow
$0.59
$0.59

比较该模型在不同 API 供应商之间的定价。

外部链接