multimodal benchmark
BenchCAD (with Python tool)
BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
BenchCAD (with Python tool) leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 83.4% | 100.0% | 3 | C | |
| 2 | OP | 78.2% | 50.0% | 3 | C | |
| 3 | OP | 73.9% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
BenchCAD (with Python tool) highlights
The top published results on this benchmark's own scale.
What is BenchCAD (with Python tool)?
Definition and scoring fields from the benchmark registry.
BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- BenchCAD (with Python tool)
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- benchcad-with-python-tool|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about BenchCAD (with Python tool).
Which model scores highest on BenchCAD (with Python tool)?
GPT-5.6 Sol is currently ranked first with 83.4%.
What does BenchCAD (with Python tool) measure?
BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.