Phi-4 Mini Instruct
MicrosoftPhiOpen WeightMIT · Commercial OK
描述
Phi 4 Mini Instruct is a lightweight (3.8B parameters) open model built upon synthetic data and filtered web data, focusing on high-quality reasoning. It supports a 128K token context length and is enhanced for instruction adherence and safety via supervised fine-tuning and direct preference optimization.
发布日期
2024-02-26
参数规模
3.8B
上下文长度
128K
支持模态
text
能力雷达图
19
general
7
coding
18
reasoning
20
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
25.2%自报
Creativity
Social IQa
72.5%自报
Arena Hard
32.8%自报
Finance
MMLU
67.3%自报
TruthfulQA
66.4%自报
MMLU-Pro
52.8%自报
General
ARC-C
83.7%自报
OpenBookQA
79.2%自报
PIQA
77.6%自报
Multilingual MMLU
49.3%自报
Language
BoolQ
81.2%自报
BIG-Bench Hard
70.4%自报
Winogrande
67.0%自报
Math
GSM8k
88.6%自报
MATH
64.0%自报
MGSM
63.9%自报
Reasoning
HellaSwag
69.1%自报
AA 评测指数
Intelligence Index8.4
Math Index6.7
Coding Index3.6
Math 5000.7
Mmlu Pro0.5
Gpqa0.3
Ifbench0.2
Lcr0.1
Livecodebench0.1
Scicode0.1
Tau20.1
Aime 250.1
Hle0.0
Aime0.0
Terminalbench Hard0.0
LLM Stats 分类评分
Math70
Psychology70
Reasoning70
Finance60
General60
Healthcare60
Language60
Legal60
Creativity50
Physics50
Writing30
Biology30
Chemistry30
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒44.6 tokens/s
首Token延迟0.33s
首回答延迟0.33s
可用提供商
(LS 内部计价单位)暂无提供商数据