Phenotype extraction on CSC (n=116 docs)
65.7F1 ScoreMistral 24B
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral 24BApproach=RDMA2025.07 | 65.7 | |
| Qwen3 32BApproach=RDMA2025.07 | 64.9 | |
| GPT-5Approach=RDMA2025.07 | 64.6 | |
| Llama-3 70BApproach=RDMA2025.07 | 62.7 | |
| Llama-3 70BApproach=RAG2025.07 | 62.4 | |
| Mistral 24BApproach=RAG2025.07 | 59.5 | |
| Qwen3 32BApproach=RAG2025.07 | 59.4 | |
| GPT-5Approach=RAG2025.07 | 54.3 | |
| Llama-3 8BApproach=RDMA2025.07 | 51.9 | |
| Llama-3 8BApproach=RAG2025.07 | 50.9 | |
| FastHPOCRApproach=Baselines2025.07 | 48 | |
| i2b2Approach=Baselines2025.07 | 46.1 | |
| BioClinicalBERTApproach=Baselines2025.07 | 39.2 | |
| BioBERT-MRCApproach=Baselines2025.07 | 38.2 | |
| PhenoGPTApproach=Baselines2025.07 | 37.3 | |
| DictionaryApproach=Baselines2025.07 | 31.9 | |
| GPT-5Approach=Zeroshot2025.07 | 0 | |
| Llama-3 70BApproach=Zeroshot2025.07 | 0 | |
| Llama-3 8BApproach=Zeroshot2025.07 | 0 | |
| Mistral 24BApproach=Zeroshot2025.07 | 0 | |
| Qwen3 32BApproach=Zeroshot2025.07 | 0 |