Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Filtering on Manually adjudicated gold-standard CUIs Ischaemic Stroke v1 (test)
Loading...
277
Total CUIs
GPT-5-mini
124.12
163.81
203.5
243.19
Feb 20, 2026
Total CUIs
Recall
Precision
F1-score
Updated 4d ago
Evaluation Results
Method
Method
Links
Total CUIs
Recall
Precision
F1-score
GPT-5-mini
Framework=CUICurate, B...
2026.02
277
90
99
94
GPT-5
Framework=CUICurate, B...
2026.02
243
79
99
88
manual
Mode=manual curation
2026.02
130
21
49
29
Feedback
Search any
task
Search any
task