| common-sense-reasoning-on-record | Turing NLR v5 XXL 5.4B (fine-tuned) | – | EM: 95.9F1: 96.4 |
| common-sense-reasoning-on-record | Vega v2 6B (fine-tuned) | – | EM: 93.9F1: 94.4 |
| coreference-resolution-on-winograd-schema | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 97.3 |
| coreference-resolution-on-winograd-schema | Vega v2 6B (KD-based prompt transfer) | – | Accuracy: 98.6 |
| natural-language-inference-on-commitmentbank | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 97.6F1: 95.9 |
| natural-language-inference-on-commitmentbank | Vega v2 6B (KD-based prompt transfer) | – | Accuracy: 99.2F1: 98.6 |
| natural-language-inference-on-rte | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 94.1% |
| natural-language-inference-on-rte | Vega v2 6B (KD-based prompt transfer) | – | Accuracy: 96% |
| question-answering-on-boolq | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 92 |
| question-answering-on-boolq | Vega v2 6B (fine-tuned) | – | Accuracy: 90.5 |
| question-answering-on-copa | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 98.2 |
| question-answering-on-copa | Vega v2 6B (KD-based prompt transfer) | – | Accuracy: 99.4 |
| question-answering-on-multirc | Turing NLR v5 XXL 5.4B (fine-tuned) | – | F1: 88.4EM: 63 |
| question-answering-on-multirc | Vega v2 6B (fine-tuned) | – | F1: 88.2EM: 62.4 |
| word-sense-disambiguation-on-words-in-context | Turing NLR v5 XXL 5.4B (fine-tuned) | – | Accuracy: 77.1 |
| word-sense-disambiguation-on-words-in-context | Vega v2 6B (fine-tuned) | – | Accuracy: 77.4 |