Agentic benchmark
AutoCAD-Bench leaderboard
Every model the catalog carries a published AutoCAD-Bench value for, ranked by that value.
CategoryAgentic
MeasureTask completion rate at a 75-point rubric threshold
Tasks21 2D drawing tasks and 29 3D modeling tasks
DifficultyProfessional CAD computer use
Published byAutoCAD-Bench
A Markov Studios computer-use benchmark that asks agents to produce 2D drawings and 3D models in AutoCAD.
No model in the catalog has a published AutoCAD-Bench score.
The benchmark is defined by AutoCAD-Bench, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.