LLM Stats (BenchCAD): leaderboard
LLM Stats compilation of vendor-reported BenchCAD results without tools: BenchCAD is built from 17,900 execution-verified CadQuery programs across 106 industrial part families, and its Vision2Code task asks the model to write CadQuery code that reproduces a part from multi-view renders, scored by voxel IoU against the reference geometry (0-1, shown as %). Higher is better. All rows are self-reported, and vendors may report different task subsets.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around August 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 5.5 | 74.7 | #13 |
| 2 | Claude Opus 5.5 | 73 | #3 |
| 3 | Kimi K3.1 Pro | 72.8 | #18 |
| 4 | GPT-5.6 Sol | 70.6 | #22 |
| 5 | Claude Haiku 5.5 | 67 | #46 |
| 6 | GPT-5.6 Luna | 63.1 | #80 |
| 7 | GPT-5.6 Terra | 62.3 | #43 |
No result here: #5 GPT-6 Astra, #6 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-benchcad · How It Works · Data refreshed daily, snapshot 2026-11-07.