Phi 4 Multimodal Instruct
Feb 2025
Phi 4 Multimodal InstructCompare inon
Phi 4 Multimodal Instruct measured on 32 of 80 Speech to text benchmarks32
BenchmarkByScoreRank
No benchmark matches
Alternatives?
ModelScoreCostPriceWhat changes
CheaperGemma 4 E4B ItOpen-50%-60%$0.02Languages: not verified+1ZBetterZoom Scribe V2 Pro+72%—$0.003Languages: loses es, fr, de +19
OpenQwen 3 ASR 1.7B Hf+21%——
BetterScribe v2+48%—$0.004SBetterSmallest AI Pulse+50%—$0.005Languages: loses ar, cs, da +9ModelScoreCostPriceWhat changes
Gemma 4 E4B ItOpen-50%-60%$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
ZZoom Scribe V2 Pro+72%—$0.003Languages: loses es, fr, de +19Scribe v2+48%—$0.004SSmallest AI Pulse+50%—$0.005Languages: loses ar, cs, da +9OSpeech v3.1+56%——Languages: loses pt, it, ko +14ModelScoreCostPriceWhat changes
Qwen 3 ASR 1.7B HfOpen+21%——OMOSS Transcribe DiarizeOpen+16%——Languages: loses es, fr, de +18
Canary Qwen 2.5B, NVIDIAOpensame—$0.001Languages: loses es, fr, de +19
Granite Speech 4.1 2B NarOpensame——Languages: loses zh, ja, it +15Granite Speech 4.1 2BOpensame——Languages: loses zh, it, ko +14Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Speech & VoiceChat & Knowledge
Humanity's Last Exam5#290
AA Intelligence Index 4.3.2≈5.8#326
GPQA Diamond31.5#317
Coding
LiveCodeBench · AA archived13.1#163
Vision & Documents
MMMU-Pro (vision)14.5#136
FAQ
How much does Phi 4 Multimodal Instruct cost?›
$0.05 per 1M billed tokens.
Is Phi 4 Multimodal Instruct free to use?›
There is no free API; it costs $0.05 per 1M billed tokens. The weights are open, so you can run it yourself.
How good is Phi 4 Multimodal Instruct, and what is it best at?›
#7 of 61 in Speech to text.
Is Phi 4 Multimodal Instruct better than Voxtral Small 24B 2507?›
On Open ASR · Earnings-22 Cleaned AA Chunked WER, Phi 4 Multimodal Instruct scores 7.1 vs 7.1 — about the same. It is 1,567% more expensive.
When was Phi 4 Multimodal Instruct released? Is there a newer version?›
Released 2025-02-24. It is the current version in its line.
Is Phi 4 Multimodal Instruct open source?›
Yes, the weights are open (MIT licence).
Can I run Phi 4 Multimodal Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Phi 4 Multimodal Instruct?›
Phi 4 Multimodal Instruct is an open-weights speech & voice model from Microsoft, released Feb 2025.
What are the best alternatives to Phi 4 Multimodal Instruct?›
Gemma 4 E4B It (cheaper), Zoom Scribe V2 Pro (better), Qwen 3 ASR 1.7B Hf (open weights).