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
基准测试分数 (LLM Stats)
Biology
GPQA
49.0%自报
Code
HumanEval
86.6%自报
LiveCodeBench
55.5%自报
Communication
MT-Bench
0.94 / 100自报
Creativity
AlignBench
81.6%自报
Arena Hard
81.2%自报
Finance
MMLU-Pro
71.1%自报
General
MBPP
0.88 / 100自报
MMLU-Redux
86.8%自报
IFEval
84.1%自报
MultiPL-E
75.1%自报
LiveBench
52.3%自报
Math
GSM8k
95.8%自报
MATH
83.1%自报
AA 评测指数
Intelligence Index15.6
Math Index14.0
Coding Index11.9
Math 5000.9
Mmlu Pro0.7
Gpqa0.5
Ifbench0.4
Tau20.3
Livecodebench0.3
Scicode0.3
Lcr0.2
Aime0.2
Aime 250.1
Terminalbench Hard0.0
Hle0.0
LLM Stats 分类评分
Communication90
Creativity90
Roleplay90
Structured Output80
Writing80
Instruction Following80
Language80
Math80
Reasoning80
Code70
Finance70
General70
Healthcare70
Legal70
Biology50
Chemistry50
Physics50
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