Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
VQA-RAD Closed-Subset Accuracy Benchmark Leaderboard | Phaseo
VQA-RAD Closed-Subset Accuracy
VQA-RAD Closed-Subset Accuracy
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: numerical
View benchmark source
Recorded Results
1
Average Score
70.20
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
Google
MedGemma 1.5 4B
13 Jan 2026
70.20
MedGemma model card benchmark table
Yes
Source
Score Range
70.20 - 70.20
Leading Model (lowest score)
70.20 - MedGemma 1.5 4B
