| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | LFM-1.3B-Distill (32K output budget) | – | Accuracy: 36.25 |
| mathematical-reasoning-on-aime24 | LFM-1.3B-Distill (32K output budget) | – | Acc: 51.04 |
| mathematical-reasoning-on-math-500 | LFM-1.3B-Distill (32K output budget) | – | Accuracy: 87.48 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | LFM-1.3B-Distill (32K output budget) | – | Accuracy: 39.29 |