Skip to main content

Phi-4 Multimodal Instruct

MicrosoftPhiOpen WeightMIT · Commercial OK

Description

Phi-4-multimodal-instruct is a lightweight (5.57B parameters) open multimodal foundation model that leverages research and datasets from Phi-3.5 and 4.0. It processes text, image, and audio inputs to generate text outputs, supporting a 128K token context length. Enhanced via SFT, DPO, and RLHF for instruction following and safety.

Release Date
2025-02-26
Parameters
5.6B
Context Length
—
Modalities
image, text

Capability Radar

70
general
0
coding
60
reasoning
51
scienceest.
42
agents
85
multimodal

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

Rankings

Domain#RankScoreSource
Multimodal Ranking137
23.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Math

MathVista62.4%SR
InterGPS48.6%SR

Multimodal

MMMU55.1%SR
Video-MME55.0%SR

Reasoning

ChartQAMasry et al. (2022)81.4%SR

Vision

ScienceQA Visual97.5%SR
DocVQADocVQA (2020)93.2%SR
MMBench86.7%SR
POPE85.6%SR
OCRBench84.4%SR
AI2D82.3%SR
TextVQA75.6%SR
InfoVQA72.7%SR
BLINK61.3%SR
MMMU-Pro38.5%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Safety
90
Image To Text
80
Multimodal
70
Reasoning
70
General
70
Vision
70
Math
60
Spatial Reasoning
60
Healthcare
60
3d
60

Pricing

Input Price$0.08 / 1M tokens
Output Price$0.32 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: MicrosoftMost Expensive: Azure
ProviderInputOutput
1MicrosoftPRIMARY
$0.08
$0.32
2Azure Cognitive Services
$0.08
$0.32
3Azure
$0.08
$0.32

Compare pricing across different API providers for this model.

External Sources