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 | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 137 | 23.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Math
MathVista
62.4%SR
InterGPS
48.6%SR
Multimodal
MMMU
55.1%SR
Video-MME
55.0%SR
Reasoning
ChartQAMasry et al. (2022)
81.4%SR
Vision
ScienceQA Visual
97.5%SR
DocVQADocVQA (2020)
93.2%SR
MMBench
86.7%SR
POPE
85.6%SR
OCRBench
84.4%SR
AI2D
82.3%SR
TextVQA
75.6%SR
InfoVQA
72.7%SR
BLINK
61.3%SR
MMMU-Pro
38.5%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Safety90
Image To Text80
Multimodal70
Reasoning70
General70
Vision70
Math60
Spatial Reasoning60
Healthcare60
3d60
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.