Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math

Benchmark Model Rank Results
mathematical-reasoning-on-aime24Phi-4-Mini-Reasoning–Acc: 57.5
mathematical-reasoning-on-math-500Phi-4-Mini-Reasoning–Accuracy: 94.6
multiple-choice-question-answering-mcqa-on-gpqa-diamondPhi-4-Mini-Reasoning–Accuracy: 52.0