| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | STREAM-MA (Claude Opus 4.6, Graph) | #8 | Accuracy: 95.83 |
| question-answering-on-humanity-s-last-exam-hle | STREAM-MA (Claude Opus 4.6, Graph) | #17 | Accuracy: 27.68 |
| mathematical-reasoning-on-aime-2026 | STREAM-MA (Claude Opus 4.6, Chain) | #20 | Accuracy: 89.58 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | STREAM-MA (Claude Opus 4.6, Chain) | #24 | Accuracy: 87.37 |