| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2026 | Thomson-1.0-Small | – | Accuracy: 90.0 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Thomson-1.0-Small | – | Accuracy: 85.4 |
| question-answering-on-humanity-s-last-exam-hle | Thomson-1.0-Small | – | Accuracy: 13.4 |