Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizationsCompare

AI2D

Benchmark
AI2D
Evaluated by
Microsoft
Release date
March 24, 2016
Version
AI2D TEST
Metric
Accuracy

Results

3 results

LatestHistory
All providersAlibaba (Tongyi)Microsoft AI
AI2D TEST results
ProviderModelScoreSourceRegistry No.
Alibaba (Tongyi)Qwen3.6-35B-A3B92.7%Source for Qwen3.6-35B-A3B on AI2D TEST (opens in a new tab)130005
Alibaba (Tongyi)Qwen3.6-Plus94.4%Source for Qwen3.6-Plus on AI2D TEST (opens in a new tab)130004
Microsoft AIPhi-4 Reasoning Vision 15B (automatic think/nothink)84.8%Source for Phi-4 Reasoning Vision 15B (automatic think/nothink) on AI2D TEST (opens in a new tab)70001
Page 1 of 1

© 2026 Densa Labs

Toggle between the data update date and the application build time.
Legal
Color theme