Home/Models/Phi 4 Mini Instruct
Microsoft logo

Phi 4 Mini Instruct

by Microsoft · Released Oct 2025

Open Source
48.9
avg score
Rank #138
Compare
Better than 50% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.08
Output $/1M
$0.35
Type
text
License
Open Source
Benchmarks
7 tested
Data updated today
About

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...

Tested on 7 benchmarks with 29.4% average. Top scores: IFEval (73.8%), BBH (HuggingFace) (38.7%), MMLU-PRO (32.6%).

Capabilities
reasoning
6.5
#182 globally
math
17.0
#210 globally
knowledge
20.3
#236 globally
language
73.8
#69 globally
general
38.7
#20 globally
speed
5.0
#95 globally
Benchmark Scores
Compare All
Tested on 7 benchmarks · Ranked across 6 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

6.5
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

17.0
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

32.6
GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

7.9
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
phi-4-mini-instruct
Specifications
  • Typetext
  • Context131K tokens (~66 books)
  • ReleasedOct 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
Microsoft logoMicrosoft$0.08
Share & Export
Tweet
Phi 4 Mini Instruct is an open-source text AI model by Microsoft, released in October 2025. It has an average benchmark score of 48.9. Context window: 131K tokens.