| arithmetic-reasoning-on-gsm8k | Claude 1.3 (0-shot chain-of-thought) | – | Accuracy: 85.2 |
| arithmetic-reasoning-on-gsm8k | Claude 2 (0-shot chain-of-thought) | – | Accuracy: 88 |
| arithmetic-reasoning-on-gsm8k | Claude Instant 1.1 (0-shot chain-of-thought) | – | Accuracy: 80.9 |
| common-sense-reasoning-on-arc-challenge | Claude 1.3 (few-shot, k=5) | – | Accuracy: 90 |
| common-sense-reasoning-on-arc-challenge | Claude 2 (few-shot, k=5) | – | Accuracy: 91 |
| common-sense-reasoning-on-arc-challenge | Claude Instant 1.1 (few-shot, k=5) | – | Accuracy: 85.7 |
| question-answering-on-quality | Claude 1.3 (5-shot) | – | Accuracy: 84.1 |
| question-answering-on-quality | Claude 2 (5-shot) | – | Accuracy: 83.2 |
| question-answering-on-quality | Claude Instant 1.1 (5-shot) | – | Accuracy: 80.5 |
| question-answering-on-triviaqa | Claude 1.3 (few-shot, k=5) | – | EM: 86.7 |
| question-answering-on-triviaqa | Claude 2 (few-shot, k=5) | – | EM: 87.5 |
| question-answering-on-triviaqa | Claude Instant 1.1 (few-shot, k=5) | – | EM: 78.9 |