Human Proficiency Exam on SAT
85.1SAT Reading ScoreClaude 3.5 Sonnet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Claude 3.5 Sonnetprompting=few-shot2024.07 | 85.1 | 95.8 | |
| GPT-4oprompting=few-shot2024.07 | 82.1 | 95.5 | |
| Llama 3 405Bprompting=few-shot2024.07 | 74.8 | 94.9 | |
| Llama 3 70Bprompting=few-shot2024.07 | 71.4 | 91.9 | |
| GPT-3.5 Turboprompting=few-shot2024.07 | 61.3 | 77.3 | |
| Llama 3 8Bprompting=few-shot2024.07 | 57.4 | 73.3 |