| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-hmmt-feb-2025 | PRISM (gpt-oss-20b; LLM Aggregate) | #8 | Accuracy: 75.6 |
| mathematical-reasoning-on-aime-2025 | PRISM (gpt-oss-20b; PRM-score Vote) | #22 | Accuracy: 90.0 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | PRISM (gpt-oss-20b; Majority Vote) | #81 | Accuracy: 71.7 |