Tool Use on Nexus (test)
58.7AccuracyLlama 3 405B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 3 405Bevaluation_mode=zero-shot2024.07 | 58.7 | |
| Llama 3 70Bevaluation_mode=zero-shot2024.07 | 56.7 | |
| GPT-4oevaluation_mode=zero-shot2024.07 | 56.1 | |
| GPT-4evaluation_mode=zero-shot2024.07 | 50.3 | |
| Mixtral 8x22Bevaluation_mode=zero-shot2024.07 | 48.5 | |
| Claude 3.5 Sonnetevaluation_mode=zero-shot2024.07 | 45.7 | |
| Llama 3 8Bevaluation_mode=zero-shot2024.07 | 38.5 | |
| GPT-3.5 Turboevaluation_mode=zero-shot2024.07 | 37.2 | |
| Mistral 7Bevaluation_mode=zero-shot2024.07 | 24.7 |