Phi-4 Mini Instruct
Released
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Intelligence Index5.7
Coding Index3.8
Math Index6.7
Reasoning & knowledge
MMLU-Pro
47%
GPQA Diamond
33%
Humanity's Last Exam
4%
Long-context reasoning
17%
Coding
LiveCodeBench
13%
SciCode
11%
Agentic & tool use
Terminal-Bench Hard
0%
τ²-Bench Telecom
8%
Math & instruction following
AIME 2025
7%
IFBench
21%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Phi-4 Mini Instruct isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →