Popular medical benchmarks intended for zero shot evaluation (no training splits available).
Tim Ossowski
OctoMed
AI & ML interests
None yet
Recent Activity
updated
a collection
8 days ago
Reasoning Traces
updated
a collection
8 days ago
Reasoning Traces
updated
a collection
8 days ago
Zero Shot Medical Benchmarks
Organizations
None yet
datasets
11
OctoMed/MedXpertQA-MM
Viewer
•
Updated
•
2k
•
18
OctoMed/MMMU-PRO-Medicine
Viewer
•
Updated
•
286
•
25
OctoMed/NEJM-Image-Challenge
Viewer
•
Updated
•
947
•
20
OctoMed/Messidor2
Viewer
•
Updated
•
1.74k
•
26
OctoMed/BCSS
Viewer
•
Updated
•
7.59k
•
19
OctoMed/CoronaHack
Viewer
•
Updated
•
5.91k
•
23
OctoMed/Aptos
Viewer
•
Updated
•
2.93k
•
26
OctoMed/BrainTumor
Viewer
•
Updated
•
3.26k
•
17
OctoMed/HeadQA
Viewer
•
Updated
•
6.77k
•
35
OctoMed/MedMCQA
Viewer
•
Updated
•
187k
•
32