Benchmark Almanac

Phi-4-mini-flash-reasoning

Phi-4-mini-flash-reasoning.

Microsoft Released 9 Jul 2025 Family Phi-4 The lab's model card
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft Jul 2025

Phi-4-mini-flash-reasoning

Open weights Small

No Epoch Capabilities Index score yet
  • AIME 2025 33.6% #137 /143
  • MATH-500 92.5% #48 /67
  • AIME 2024 52.3% #73 /87

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Math and science

BenchmarkScoreRankSource
MATH-500 92.5% #48 of 67 Model card
AIME 2024 52.3% #73 of 87 Model card
GPQA Diamond 45.1% #245 of 284 Model card
AIME 2025 33.6% #137 of 143 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it.