multimodal benchmark
BenchCAD (with Python tool) Leaderboard
BenchCAD (with Python tool) is a multimodal benchmark variant evaluated with access to a Python tool for programmatic CAD reasoning.
Updated Oct 23, 2026
Models7
Model coverage7
MetricScore
EvidenceB
BenchCAD (with Python tool) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score96.30% | Percentile100.00% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score96.20% | Percentile83.33% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score95.90% | Percentile66.67% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelAN | Score87.00% | Percentile50.00% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score83.40% | Percentile33.33% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score78.20% | Percentile16.67% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score73.90% | Percentile0.00% | Participants7 | EvidenceC | Evaluated |
BenchCAD (with Python tool) Highlights
The leading models and scores on this benchmark.
BenchCAD (with Python tool) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BenchCAD (with Python tool)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BenchCAD (with Python tool)?
What BenchCAD (with Python tool) measures and how its scores work.
BenchCAD (with Python tool) is a multimodal benchmark variant for programmatic CAD reasoning with access to a Python tool.
It reports a Score measured as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BenchCAD (with Python tool)
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BenchCAD (with Python tool).
Which model scores highest on BenchCAD (with Python tool)?
Claude Sonnet 5.5 is currently ranked first with 96.30%.
What are the top three models on BenchCAD (with Python tool)?
The current leaders are Claude Sonnet 5.5 (96.30%), Claude Opus 5.5 (96.20%), and GPT-6 Astra (95.90%).
Which BenchCAD (with Python tool) model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among BenchCAD (with Python tool) results?
The fastest matched records are GPT-5.6 Luna (215.52 tok/s via OpenAI), GPT-5.6 Terra (43.35 tok/s via OpenAI), and Claude Sonnet 5.5 (42.00 tok/s via Anthropic).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.