| arithmetic-reasoning-on-gsm8k | Claude 3 Haiku | – | Accuracy: 88.9 |
| arithmetic-reasoning-on-gsm8k | Claude 3 Opus | – | Accuracy: 95.0 |
| arithmetic-reasoning-on-gsm8k | Claude 3 Sonnet | – | Accuracy: 92.3 |
| code-generation-on-humaneval | Claude 3 Opus | – | Pass@1: 84.9 |
| math-word-problem-solving-on-math | Claude 3 Haiku | – | Accuracy: 38.9 |
| math-word-problem-solving-on-math | Claude 3 Opus | – | Accuracy: 60.1 |
| math-word-problem-solving-on-math | Claude 3 Sonnet | – | Accuracy: 43.1 |
| math-word-problem-solving-on-mgsm-0-shot | Claude 3 Haiku | – | Accuracy: 75.1 |
| math-word-problem-solving-on-mgsm-0-shot | Claude 3 Opus | – | Accuracy: 90.7 |
| math-word-problem-solving-on-mgsm-0-shot | Claude 3 Sonnet | – | Accuracy: 83.5 |
| multi-task-language-understanding-on-mmlu | Claude 3 Haiku | – | Average (%): 75.2 |
| multi-task-language-understanding-on-mmlu | Claude 3 Opus | – | Average (%): 86.8 |
| multi-task-language-understanding-on-mmlu | Claude 3 Sonnet | – | Average (%): 79.0 |
| multimodal-reasoning-on-mmmu | Claude 3 Haiku | – | Accuracy: 50.2 |
| multimodal-reasoning-on-mmmu | Claude 3 Opus | – | Accuracy: 59.4 |
| multimodal-reasoning-on-mmmu | Claude 3 Sonnet | – | Accuracy: 53.1 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Claude 3 Haiku | – | Accuracy: 33.3 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Claude 3 Opus | – | Accuracy: 50.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Claude 3 Sonnet | – | Accuracy: 40.4 |