Logical Reasoning On Big Bench Formal
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| scaling-language-models-methods-analysis-1 | 50.7 |
| bloomberggpt-a-large-language-model-for | 53.6 |
| bloomberggpt-a-large-language-model-for | 52.8 |
| bloomberggpt-a-large-language-model-for | 54 |
| palm-2-technical-report-1 | 64.8 |
| bloomberggpt-a-large-language-model-for | 52.8 |
| training-compute-optimal-large-language | 52.1 |
| bloomberggpt-a-large-language-model-for | 50.8 |
| palm-2-technical-report-1 | 57.2 |