Common Sense Reasoning On Big Bench Causal
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| bloomberggpt-a-large-language-model-for | 52.41 |
| palm-2-technical-report-1 | 62.0 |
| bloomberggpt-a-large-language-model-for | 49.73 |
| bloomberggpt-a-large-language-model-for | 51.87 |
| palm-2-technical-report-1 | 58.8 |
| training-compute-optimal-large-language | 57.4 |
| bloomberggpt-a-large-language-model-for | 61.0 |
| bloomberggpt-a-large-language-model-for | 51.87 |
| scaling-language-models-methods-analysis-1 | 50.8 |