Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
BenchCAD 2.1 Core
Multimodal
Agents
Share
Official website
CAD modeling evaluation, Core subset as labeled by OpenAI; kept separate from the with-tools variant.
Ranking
Sources
#
Model
Score
1
GPT-6.2 Astra
OpenAI · max
82.5
%
2
GPT-6.2 Sol
OpenAI · max
73.1
%
3
GPT-6 Astra
OpenAI · max
62.6
%
4
GPT-6.1 Sol
OpenAI · max
52.6
%
4 models total