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.
發布日期
2024-09-19
參數規模
72.7B
上下文長度
33K
支援模態
text
能力雷達圖
31
general
19
coding
29
reasoning
32
science估算
0
agents
0
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Biology
GPQA
49.0%自報
Code
HumanEval
86.6%自報
LiveCodeBench
55.5%自報
Communication
MT-Bench
0.94 / 100自報
Creativity
AlignBench
81.6%自報
Arena Hard
81.2%自報
Finance
MMLU-Pro
71.1%自報
General
MBPP
0.88 / 100自報
MMLU-Redux
86.8%自報
IFEval
84.1%自報
MultiPL-E
75.1%自報
LiveBench
52.3%自報
Math
GSM8k
95.8%自報
MATH
83.1%自報
AA 評測指數
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 分類評分
Communication90
Creativity90
Roleplay90
Structured Output80
Writing80
Instruction Following80
Language80
Math80
Reasoning80
Code70
Finance70
General70
Healthcare70
Legal70
Biology50
Chemistry50
Physics50
定價
輸入價格$0.36 / 1M tokens
輸出價格$0.4 / 1M tokens
混合價格(3:1)$0.37 / 1M tokens
速度
Tokens/秒54.7 tokens/s
首Token延遲1.08s
首回答延遲1.08s
可用提供商
(LS 內部計價單位)暫無提供商資料