| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-olympiadbench | Stratagem (All Games) | #44 | Accuracy: 39.9 |
| multi-task-language-understanding-on-mmlu-pro | Stratagem (All Games) | #101 | Accuracy: 57.83 |
| mathematical-reasoning-on-aime24 | Stratagem (All Games) | #119 | Acc: 20.0 |
| mathematical-reasoning-on-aime-2025 | Stratagem (Kuhn Poker) | #139 | Accuracy: 13.3 |