| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2026 | Self-Organizing Agent Teams (SAT) | – | Accuracy: 71.2 |
| mathematical-reasoning-on-aime24 | Self-Organizing Agent Teams (SAT) | – | Acc: 84.7 |
| mathematical-reasoning-on-hmmt-feb-2026 | Self-Organizing Agent Teams (SAT) | – | Accuracy: 39.4 |