Logical Reasoning On Big Bench Penguins In A
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| bloomberggpt-a-large-language-model-for | 33.56 |
| scaling-language-models-methods-analysis-1 | 40.6 |
| bloomberggpt-a-large-language-model-for | 28.08 |
| palm-2-technical-report-1 | 84.9 |
| bloomberggpt-a-large-language-model-for | 40.41 |
| palm-2-technical-report-1 | 65.8 |
| bloomberggpt-a-large-language-model-for | 37.67 |
| training-compute-optimal-large-language | 48.7 |
| bloomberggpt-a-large-language-model-for | 44.5 |