BIM-Edit: leaderboard
Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions. In engineering practice, this requires more than creating new geometry, models must also understand existing scenes, edit them correctly, and preserve semantics and relations. However, many CAD benchmarks focus on creating new models rather than editing exist
Metric: Final (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 49.48 | #99 |
| 2 | Qwen 3.6 Plus | 47.63 | #120 |
| 3 | Claude Sonnet 4.6 | 45.31 | #90 |
| 4 | GPT-5.4 Pro (xHigh) | 43.94 | #32 (GPT-5.4 Pro) |
| 5 | DeepSeek V3.2 | 43.21 | #205 |
| 6 | GPT-5.4 Mini | 39.79 | #212 |
| 7 | Gemma 4 31B | 37.54 | #200 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bim-edit · How It Works · Data refreshed daily, snapshot 2026-10-20.