Phi-3 Mini Instruct 3.8B

by Microsoft

Released · 57 days after Phi-4 Mini Instruct

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index4.3
Math Index0.3
Reasoning & knowledge
MMLU-Pro
44%
GPQA Diamond
32%
Humanity's Last Exam
5%
Long-context reasoning
3%
Coding
LiveCodeBench
12%
SciCode
9%
Agentic & tool use
Terminal-Bench Hard
0%
τ²-Bench Telecom
0%
Math & instruction following
AIME 2025
0%
IFBench
24%

Available routes

No routes currently available — Phi-3 Mini Instruct 3.8B isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Available models from Microsoft

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Phi-3 Mini Instruct 3.8B — release date & benchmarks | Opper AI