Skip to main content

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
2025-02-26
Parameters
3.8B
Context Length
—
Modalities
—

Capability Radar

70
general
0
coding
70
reasoning
26
scienceest.
49
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU67.3%SR
TruthfulQA66.4%SR
Multilingual MMLU49.3%SR
Arena Hard32.8%SR

Language

BoolQ81.2%SR
MMLU-Pro52.8%SR

Math

MATH-50094.6%SR
GSM8k88.6%SR
MATH64.0%SR
MGSM63.9%SR
AIMEMAA57.5%SR

Reasoning

ARC-C83.7%SR
OpenBookQA79.2%SR
PIQA77.6%SR
Social IQa72.5%SR
BIG-Bench Hard70.4%SR
HellaSwagAI2 (2019)69.1%SR
Winogrande67.0%SR
GPQANYU + Cohere + Anthropic (2023)52.0%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Math
70
Psychology
70
Reasoning
70
General
70
Language
60
Legal
60
Finance
60
Healthcare
60
Physics
50
Creativity
50
Chat
30
Biology
30
Chemistry
30
Writing
30

Pricing

Input Price$0.075 / 1M tokens
Output Price$0.3 / 1M tokens

Speed

Tokens/sec44.5
Time to First Token0.90s
Time to Answer0.90s

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: MicrosoftMost Expensive: Azure
ProviderInputOutput
1MicrosoftPRIMARY
$0.075
$0.3
2Azure Cognitive Services
$0.075
$0.3
3Azure
$0.075
$0.3

Compare pricing across different API providers for this model.

External Sources