Phi-4-instruct (reasoning-trained) Benchmark Details
Phi-4-instruct (reasoning-trained) currently shows benchmark results led by AIME 2024 (46 / 62, score 50), MATH-500 (36 / 44, score 90.40), GPQA Diamond (156 / 179, score 49).
Benchmark Results
Phi-4-instruct (reasoning-trained)
Benchmark Results
Math and Reasoning
2 evaluationsBenchmark / mode
Score
Rank/total