| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | Claude 3.5 Sonnet (HPT) | #1 | Accuracy: 97.72 |
| common-sense-reasoning-on-commonsenseqa | GPT-4o (HPT) | #1 | Accuracy: 92.54 |
| question-answering-on-boolq | Mistral-Nemo 12B (HPT) | #1 | Accuracy: 99.87 |
| text-summarization-on-samsum-corpus | GPT-4o (HPT) | #7 | ROUGE-L: 30 |