Question Answering On Bamboogle
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| fireact-toward-language-agent-fine-tuning | 44.0 |
| answering-questions-by-meta-reasoning-over | 66.5 |
| measuring-and-narrowing-the-compositionality | 57.6 |
| rest-meets-react-self-improvement-for-multi | 76.1 |
| measuring-and-narrowing-the-compositionality | 60.0 |
| measuring-and-narrowing-the-compositionality | 0 |
| measuring-and-narrowing-the-compositionality | 46.4 |
| making-retrieval-augmented-language-models | 62.7 |
| measuring-and-narrowing-the-compositionality | 17.6 |