Phi-4-mini-reasoning model card (Hugging Face) Apr 30, 2025
- MATH-500 94.6
- GPQA Diamond 52
Phi-4-mini-reasoning
Phi-4-mini-reasoning.
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft Apr 2025 Phi-4-mini-reasoning
Open weights Small
No Epoch Capabilities Index score yet
- MATH-500 94.6% #41 /70
- AIME 2024 57.5% #71 /88
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 94.6% | #41 of 70 | Lab model card | |
| GPQA Diamond | 52% | #238 of 302 | Lab model card | |
| AIME 2024 | 57.5% | #71 of 88 | Lab model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BRIDGE | 21.3 | #38 of 39 | Official leaderboard |
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. 1 of them isn't in the launch post.
Capabilities
- AIME 2024 57.5
- MATH-500 94.6
- GPQA Diamond 52