Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long Length of Stay Prediction on EHRSHOT Long Length of Stay
Loading...
74.12
Accuracy
EHR-RAG
63.1064
65.9657
68.825
71.6843
Jan 29, 2026
Accuracy
Macro F1
F1 (Short)
F1 (Long)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Macro F1
F1 (Short)
F1 (Long)
EHR-RAG
Backbone LLM=GPT-5
2026.01
74.12
70.15
81.03
59.26
Direct Generation
Backbone LLM=GPT-5
2026.01
69.41
66.52
76.36
56.67
RAG
Backbone LLM=GPT-5
2026.01
68.24
64.77
75.82
53.71
Uniform RAG
Backbone LLM=GPT-5
2026.01
65.1
61.5
73.27
49.72
ReAct RAG
Backbone LLM=GPT-5
2026.01
65.1
60.85
73.75
47.95
Rule-based RAG
Backbone LLM=GPT-5
2026.01
63.53
56.58
73.95
39.22
Feedback
Search any
task
Search any
task