Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
ScienceQA Visual Benchmark Leaderboard | Phaseo
ScienceQA Visual
ScienceQA Visual
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: percentage
Multimodal
Recorded Results
1
Average Score
97.50%
Score Range
97.50% - 97.50%
Leading Model (lowest score)
97.50% - Phi 4 multimodal instruct
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
Microsoft
Phi 4 multimodal instruct
01 Feb 2025
97.50%
-
Yes
Source
