Qwen2.5 7B Instruct
Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK
描述
Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.
發布日期
2024-09-19
參數規模
7.6B
上下文長度
33K
支援模態
text
能力雷達圖
60
general
60
coding
70
reasoning
34
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
暫無排名資料
基準測試分數 (LLM Stats)
Biology
GPQA
36.4%自報
Code
HumanEval
84.8%自報
LiveCodeBench
28.7%自報
Communication
MT-Bench
0.88 / 100自報
Creativity
AlignBench
73.3%自報
Arena Hard
52.0%自報
Finance
MMLU-Pro
56.3%自報
General
MBPP
0.79 / 100自報
MMLU-Redux
75.4%自報
IFEval
71.2%自報
MultiPL-E
70.4%自報
LiveBench
35.9%自報
Math
GSM8k
91.6%自報
MATH
75.5%自報
AA 評測指數
暫無 AA 評測資料
LLM Stats 分類評分
Communication90
Roleplay80
Structured Output70
Creativity70
Instruction Following70
Language70
Math70
Writing60
Code60
Finance60
General60
Healthcare60
Legal60
Reasoning60
Biology40
Chemistry40
Physics40
定價
輸入價格$0.04 / 1M tokens
輸出價格$0.1 / 1M tokens
混合價格(3:1)$0.055 / 1M tokens
速度
暫無速度資料
可用提供商
(LS 內部計價單位)暫無提供商資料