Human Proficiency Exam on GRE
166GRE Quant Scaled ScoreGPT-4o
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4oprompting=few-shot2024.07 | 166 | 89.3 | — | |
| Claude 3.5 Sonnetprompting=few-shot2024.07 | 164 | 90.7 | — | |
| Llama 3 405Bprompting=few-shot2024.07 | 162 | 80 | — | |
| Nemotron 4 340Bprompting=few-shot2024.07 | 161 | — | — | |
| Llama 3 70Bprompting=few-shot2024.07 | 158 | 74.7 | — | |
| GPT-3.5 Turboprompting=few-shot2024.07 | 155 | 50.7 | — | |
| Llama 3 8Bprompting=few-shot2024.07 | 152 | 48 | — |