| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-simpleqa | Trinity Large Preview | #6 | Accuracy: 23.92 |
| sentence-completion-on-hellaswag | Trinity Large Base (5-shot) | #17 | Accuracy: 90.11 |
| common-sense-reasoning-on-winogrande | Trinity Large Base (5-shot) | #30 | Accuracy: 80.82 |
| multi-task-language-understanding-on-mmlu-pro | Trinity Large Preview | #56 | Accuracy: 75.25 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Trinity Large Preview | #90 | Accuracy: 63.32 |
| mathematical-reasoning-on-aime-2025 | Trinity Large Preview | #118 | Accuracy: 24.36 |