Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Close-ended QA on PubMedQA
Loading...
85
Accuracy
Fine-Tuned GPT-4o + MedBioRAG
16.672
34.411
52.15
69.889
Dec 10, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Fine-Tuned GPT-4o + MedBioRAG
Backbone=GPT-4o, Fine-...
2025.12
85
Fine-Tuned GPT-4o
Backbone=GPT-4o, Fine-...
2025.12
80.7
GPT-4o-mini
Backbone=GPT-4o-mini,...
2025.12
77.55
GPT-4o-mini + MedBioRAG
Backbone=GPT-4o-mini,...
2025.12
76.32
GPT-4 + MedBioRAG
Backbone=GPT-4, Fine-t...
2025.12
72.81
GPT-4o + MedBioRAG
Backbone=GPT-4o, Fine-...
2025.12
66.67
GPT-4
Backbone=GPT-4, Fine-t...
2025.12
52.63
GPT-4o
Backbone=GPT-4o, Fine-...
2025.12
44.74
GPT-3.5 + MedBioRAG
Backbone=GPT-3.5, Fine...
2025.12
38.6
GPT-3.5
Backbone=GPT-3.5, Fine...
2025.12
19.3
Feedback
Search any
task
Search any
task