Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Acute Problems Prediction on RealICU-Scale (test)
Loading...
85.2
Hit@5
ICU-Evo
23.008
39.154
55.3
71.446
May 13, 2026
Hit@5
R@5
Updated 20d ago
Evaluation Results
Method
Method
Links
Hit@5
R@5
ICU-Evo
Backbone=GPT-5.4 [22],...
2026.05
85.2
56.2
ICU-Evo
Backbone=Gemini-3.1-pr...
2026.05
82.7
51.8
ICU-Evo
Backbone=Qwen3-235B [3...
2026.05
64.9
37.5
RAG
Backbone=GPT-5.4 [22],...
2026.05
58.4
32.1
RAG
Backbone=Gemini-3.1-pr...
2026.05
56.8
31.5
Local-window
Backbone=Gemini-3.1-pr...
2026.05
48.7
26.5
Local-window
Backbone=GPT-5.4 [22],...
2026.05
47.5
26.6
Full-context
Backbone=Qwen3-235B [3...
2026.05
40.1
23.2
RAG
Backbone=Qwen3-235B [3...
2026.05
37.9
20.7
Local-window
Backbone=Qwen3-235B [3...
2026.05
25.4
14.2
Feedback
Search any
task
Search any
task