Phi 4 multimodal instruct

Microsoft · microsoft/phi-4-multimodal-instruct

ProviderMicrosoft
Familyphi
Typeaudio-asr
Statusactive
Released2025-02-24

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AlpacaEvalunassessed32.5
Arena Elo — Codingunassessed1250
Arena Elo — Mathunassessed1260
Arena Elo — Overall (Text)unassessed1240
BIG-Bench Hardunassessed54.3
GPQA Diamondunassessed52.5
HumanEvalunassessed78.5
IFEvalunassessed78
MATH-500unassessed82.5
MMLU: Astronomyunassessed68.8
MMLU: Biology (subcategory)unassessed77.8
MMLU: Business Ethicsunassessed70.2
MMLU: Chemistry (subcategory)unassessed70.5
MMLU: Clinical Knowledgeunassessed76.2
MMLU: Computer Science (subcategory)unassessed78.5
MMLU: Jurisprudenceunassessed66.8
MMLU: Physics (unresolved key)unassessed74.2
MMLU-Prounassessed68.5
MMLU: Professional Accountingunassessed61.2
MMLU: Professional Lawunassessed65.5
MT-Benchunassessed8.2
MuSRunassessed23.5
WildBenchunassessed58.2

Data

This card as JSON · Edit on GitHub