Question Answering On Pubmedqa
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy |
|---|---|
| mediswift-efficient-sparse-pre-trained | 76.8 |
| large-language-models-encode-clinical | 34 |
| biogpt-generative-pre-trained-transformer-for | 78.2 |
| large-language-models-encode-clinical | 57.8 |
| domain-specific-language-model-pretraining | 55.84 |
| the-claude-3-model-family-opus-sonnet-haiku | 75.8 |
| evaluation-of-large-language-model | 76.80 |
| galactica-a-large-language-model-for-science-1 | 77.6 |
| pubmedqa-a-dataset-for-biomedical-research | 78.0 |
| bioelectra-pretrained-biomedical-text-encoder | 64.2 |
| linkbert-pretraining-language-models-with | 70.2 |
| galactica-a-large-language-model-for-science-1 | 73.6 |
| large-language-models-encode-clinical | 79 |
| towards-expert-level-medical-question | 74.0 |
| towards-expert-level-medical-question | 75.0 |
| large-language-models-encode-clinical | 77.2 |
| biomedgpt-open-multimodal-generative-pre | 76.1 |
| large-language-models-encode-clinical | 55 |
| towards-expert-level-medical-question | 79.2 |
| linkbert-pretraining-language-models-with | 72.2 |
| galactica-a-large-language-model-for-science-1 | 70.2 |
| meditron-70b-scaling-medical-pretraining-for | 81.6 |
| biogpt-generative-pre-trained-transformer-for | 81.0 |
| the-claude-3-model-family-opus-sonnet-haiku | 74.9 |
| can-large-language-models-reason-about | 78.2 |
| the-cot-collection-improving-zero-shot-and | 73.42 |
| large-language-models-encode-clinical | 75.2 |
| large-language-models-encode-clinical | 67.6 |
| rankrag-unifying-context-ranking-with | 79.8 |