MicrosoftProvisional

Phi-4 mini instruct

Phi / Phi-4 mini instruct · microsoft/Phi-4-mini-instruct

Microsoft small open model for efficient local and edge workflows.

Objective score

2.9

Confidence

76%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Scenario evidence

Six task-specific rankings

Feature development#78Obj. 2.90 · 0%Debug and repair#79Obj. 2.80 · 0%Refactoring#79Obj. 2.80 · 0%Code review#79Obj. 2.90 · 0%Large-repo agent work#77Obj. 2.90 · 0%Frontend / UI#79Obj. 2.80 · 0%

Evidence state

Signal coverage

Benchmarks: 1
Rank points: 8
Usage: 0
Agent: 0
Sources: 3

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 3.8
Openrouter Usage: —
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#77 · 4

Aug 1#77 · 4

Aug 1#77 · 4

Jul 31#77 · 4

Jul 31#77 · 4

Jul 31#77 · 4

Usage signals

Evidence is being collected. Missing data is not treated as zero.

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Microsoft Phi-4 mini model card documents MIT/open-weight status and context.Artificial Analysis Coding Agents · ok Microsoft Phi-4 mini model card · ok NVIDIA Nemotron 3 Nano model card · ok