Phi-4 Mini Instruct
MicrosoftPhiOpen WeightMIT · Commercial OK
Description
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.
Release Date
2024-02-26
Parameters
3.8B
Context Length
128K
Modalities
text
Capability Radar
19
general
7
coding
18
reasoning
20
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 427 | 9.0 | AA |
| General Ranking | 452 | 17.0 | AA |
| Math Reasoning | 310 | 18.0 | AA |
| Reasoning | 50 | 69.0 | LS |
| Science | 425 | 18.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
25.2%SR
Creativity
Social IQa
72.5%SR
Arena Hard
32.8%SR
Finance
MMLU
67.3%SR
TruthfulQA
66.4%SR
MMLU-Pro
52.8%SR
General
ARC-C
83.7%SR
OpenBookQA
79.2%SR
PIQA
77.6%SR
Multilingual MMLU
49.3%SR
Language
BoolQ
81.2%SR
BIG-Bench Hard
70.4%SR
Winogrande
67.0%SR
Math
GSM8k
88.6%SR
MATH
64.0%SR
MGSM
63.9%SR
Reasoning
HellaSwag
69.1%SR
AA Evaluation Indices
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 Category Scores
Math70
Psychology70
Reasoning70
Finance60
General60
Healthcare60
Language60
Legal60
Creativity50
Physics50
Writing30
Biology30
Chemistry30
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec44.6 tokens/s
Time to First Token0.33s
Time to Answer0.33s
Available Providers
(LS internal units)No provider data available