Zero Shot Learning On Medconceptsqa
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| gpt-4-technical-report-1 | 52.489 |
| clinical-longformer-and-clinical-bigbird | 25.040 |
| biomedgpt-open-multimodal-generative-pre | 24.747 |
| gatortron-a-large-clinical-language-model-to | 24.862 |
| zephyr-direct-distillation-of-lm-alignment | 25.538 |
| small-language-models-learn-enhanced | 25.680 |
| Modèle 7 | 24.427 |
| llama-open-and-efficient-foundation-language-1 | 25.840 |
| biomistral-a-collection-of-open-source | 24.569 |
| meditron-70b-scaling-medical-pretraining-for | 25.360 |
| language-models-are-few-shot-learners | 37.058 |
| meditron-70b-scaling-medical-pretraining-for | 25.751 |
| biobert-a-pre-trained-biomedical-language | 26.151 |