Natural Language Inference On Commitmentbank
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| designing-effective-sparse-expert-models | 98 |
| bloomberggpt-a-large-language-model-for | 44.64 |
| bloomberggpt-a-large-language-model-for | 48.21 |
| designing-effective-sparse-expert-models | 98.2 |
| n-grammer-augmenting-transformers-with-latent-1 | 67.9 |
| language-models-are-few-shot-learners | 75.6 |
| palm-2-technical-report-1 | 82.1 |
| bloomberggpt-a-large-language-model-for | 48.21 |
| palm-2-technical-report-1 | 80.4 |
| language-models-are-few-shot-learners | - |
| palm-2-technical-report-1 | 87.5 |
| exploring-the-limits-of-transfer-learning | 96.8 |
| bloomberggpt-a-large-language-model-for | 53.57 |
| exploring-the-limits-of-transfer-learning | 94.4 |
| palm-scaling-language-modeling-with-pathways-1 | 100 |
| toward-efficient-language-model-pretraining | 97.6 |
| toward-efficient-language-model-pretraining | 99.2 |
| alexatm-20b-few-shot-learning-using-a-large | 67.9 |
| deberta-decoding-enhanced-bert-with | 97.2 |
| exploring-the-limits-of-transfer-learning | 94 |