Benchmarks for AI Models and Agents on CAD Tasks
Parametric CAD Bench is a comprehensive collection of benchmarks to benchmark CAD models and AI agents on CAD design and 3D modeling tasks.
A community effort to build the best open parametric CAD datasets, initiated by the gNucleus AI team.
Dataset
gnucleus.ai
Leaderboard
View full leaderboard →| Rank | Model | Agent | Geom Score | Spec Score | Combined | Cost (USD) |
|---|---|---|---|---|---|---|
1 | claude-opus-5(max) | claude-code | 88.9 | 97.2 | 90.6 | $113.24 |
2 | grok-4.6(high) | grok-build | 83.5 | 97.2 | 87.8 | $69.23 |
3 | gpt-5.6-sol(max) | codex | 84.8 | 94.3 | 86.5 | $97.58 |
4 | grok-4.5(high) | grok-build | 80.2 | 94.1 | 83.7 | $36.59 |
5 | gpt-5.5(high) | codex | 80.8 | 93.9 | 83.2 | $170.00 |
6 | gemini-3.1-pro-preview(high) | mini-swe-agent | 74.2 | 95.4 | 79.0 | $70.82 |
7 | gpt-5.5(high) | mini-swe-agent | 71.4 | 89.3 | 74.4 | $42.35 |
8 | claude-opus-4-7(max) | mini-swe-agent | 69.3 | 89.0 | 73.4 | $29.84 |
9 | gemini-3.1-pro-preview(high) | gemini-cli | 68.9 | 83.9 | 72.9 | $51.28 |
10 | claude-opus-4-7(max) | claude-code | 62.4 | 83.3 | 65.5 | $73.25 |
Benchmarks Tasks
Run Benchmark →3D Parametric Part Generation
Generate editable, parametric 3D CAD part models from natural-language prompts and reference inputs.
Assembly Generation
Generate multi-part assemblies with proper mates, constraints, and component hierarchy.
Complex CAD workflow
Multi-step CAD workflows that generate, iteratively edit, and verify designs until the model meets the target spec.
Evaluation Methods
View Evaluator →CAD evaluation should check not only visual similarity, but also whether the generated CAD is valid, accurate, rebuildable, and consistent with the design spec.
Each task is scored automatically in a sandboxed CAD environment, comparing the generated CAD against the design spec and reference CAD (ground truth) across the axes below. Scoring is deterministic — same output, same score.
Geometry Accuracy
Measures how closely the generated geometry matches the reference part.
Constraint & Assembly Correctness
Checks constraint satisfaction, mating validity, and assembly stability.
Parametric Correctness
Verifies CAD model consistency with the spec parameters.
Topology / Structure
Evaluates topological validity and part structure correctness.
Agent Workflow Success
Assesses task completion rate and workflow correctness.
Efficiency
Measures token usage, execution time, and resource efficiency.
Latest Updates
August 12, 2026
Four new (agent, model) cells join the board, taking the top four spots and pushing the leaderboard to 14 entries. Claude Opus 5 via Claude Code leads at 0.906 — the first result above 0.9 — closing 44% of the remaining gap to a perfect score while costing less than the previous leader. Grok 4.6 offers the best balance of cost and performance, delivering 96.9% of the top score at just 61% of the cost. In the 90 days since the May run the engineering slice moved sharply — the weakest new cell would have ranked first in May, and the gain went almost entirely into geometry rather than spec.
May 13, 2026
A new benchmark for AI agents that design parametric 3D mechanical parts in FreeCAD. Multi-step agentic loop scoring geometric correctness and consistency between the generated CAD and the provided spec, across 10 agent–model combinations spanning frontier vendors. Early results: GPT-5.5 via Codex leads at 0.832 with a visible harness effect — and is also the most expensive combination at $170.
May 10, 2026
A programmatic grader for evaluating AI-generated parametric FreeCAD parts — checks geometry similarity to the ground truth and CAD/spec consistency.
May 08, 2026
Open-sourced cad-gen-freecad on HuggingFace — native FreeCAD parts with parametric feature history, design specs, and renderings, aimed at accurate, parametric CAD generation from text prompt.