Answerability Prediction On Peerqa
Metrics
Macro F1
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Macro F1 |
|---|---|
| Model 1 | 0.4197 |
| language-models-are-few-shot-learners | 0.3304 |
| mistral-7b | 0.4703 |
| the-llama-3-herd-of-models | 0.2881 |
| gpt-4-technical-report-1 | 0.3087 |
| the-llama-3-herd-of-models | 0.3112 |