Better than 57% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data updated today
About
Microsoft text generation model. 879K downloads on HuggingFace.
Tested on 6 benchmarks with 28.2% average. Top scores: IFEval (57.8%), BBH (HuggingFace) (36.8%), MMLU-PRO (32.9%).
Capabilities
reasoning
10.1
#135 globally
math
19.6
#164 globally
knowledge
22.4
#188 globally
language
57.8
#92 globally
general
36.8
#21 globally
Benchmark Scores
Compare AllTested on 6 benchmarks · Ranked across 5 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
10.1—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
19.6—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
32.9—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
12.0—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
vs Grok 4 Fast
vs Gemma 2 27B
vs Qwen3 32B Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
microsoft-phi-35-mini-instruct
Specifications
- Typetext-generation
- ContextN/A
- ReleasedAug 2024
- LicenseOpen Source
- StatusActive
Available On
MicrosoftTBDLearn More
Share & Export
Frequently Asked Questions
Phi 3.5 Mini Instruct is an open-source text-generation AI model by Microsoft, released in August 2024. It has an average benchmark score of 51.5.