BIM-Edit - Topology: leaderboard
BIM-Edit (2026) has LLM agents edit Building Information Models in IFC format from natural-language instructions (create, update and delete; direct, spatial or topological references) over 324 tasks. This board is the topology score on a 0 to 100 scale, whether relations such as hosting and containment are preserved; higher is better.
Metric: Topology score (0-100): weighted F1 of edited nodes (0.3) and edited relations (0.7) in the IFC difference graph against the reference edit, on 324 natural-language create, update and delete tasks on 11 real and 36 synthetic IFC building models (direct, spatial and topological instructions), the model edits the IFC file as an agent that runs Python through a single IfcOpenShell execution tool with a 20-call budget, temperature 0 where settable; mean over tasks; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 Plus | 47.77 | #222 |
| 2 | Claude Sonnet 4.6 | 46.19 | #161 |
| 3 | DeepSeek V3.2 | 43.86 | #406 |
| 4 | GPT-5.4 Pro (xHigh) | 42.97 | #85 (GPT-5.4 Pro) |
| 5 | Gemini 3 Flash (Preview) | 37.77 | #144 |
| 6 | Gemma 4 31B (IT) | 37.75 | #342 |
| 7 | GPT-5.4 Mini | 35.38 | #389 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=bim-edit-topology · How It Works · Data refreshed daily, snapshot 2026-11-13.