Better than 52% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
9 tested
Data updated today
About
Microsoft text generation model. 584K downloads on HuggingFace.
Tested on 9 benchmarks with 29.4% average. Top scores: IFEval (73.8%), BBH (HuggingFace) (38.7%), MMLU-PRO (32.6%).
Capabilities
reasoning
6.5
#156 globally
math
17.0
#177 globally
knowledge
20.3
#197 globally
language
73.8
#62 globally
speed
8.2
#67 globally
general
38.7
#19 globally
Benchmark Scores
Compare AllTested on 9 benchmarks · Ranked across 6 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
6.5—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
17.0—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
32.6—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
7.9—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
vs Mistral 7B V0.1
vs Claude 3.7 Sonnet
vs Qwen3 4B Thinking 2507 Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
microsoft-phi-4-mini-instruct
Specifications
- Typetext-generation
- ContextN/A
- ReleasedFeb 2025
- LicenseOpen Source
- StatusActive
Available On
MicrosoftTBDLearn More
Share & Export
Frequently Asked Questions
Phi 4 Mini Instruct is an open-source text-generation AI model by Microsoft, released in February 2025. It has an average benchmark score of 48.9.