AIME
AI benchmark results and model performance
Type: percentageMath
Recorded results
2
Average score
57.50%
Score range
57.50% - 57.50%
Leading model
57.50% - Phi 4 Mini Flash Reasoning
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Phi 4 Mini Flash Reasoning | - | 57.50% | inferred modality/version alias from phi-4-mini-reasoning | Yes | Source | |
| Phi 4 Mini Reasoning | 30 Apr 2025 | 57.50% | - | Yes | Source |
