BIM-Edit
Agents create, change, or delete elements in IFC building models. The evaluator checks the resulting geometry, attributes, and relationships.
The authors define 324 edits across 11 realistic models and 36 synthetic scenes. ONESTRUCTION used its own grader and raised the turn limit.
- Released
- June 2026
- Kind
- CAD models
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Civil engineering
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Written by experts, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Image, video and 3D generation
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 87.7%
Best score per model from ONESTRUCTION’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
- 87.7
Gemini 4 Argon
- 84.3 GPT-6 Astra
- 84.3
DeepSeek V4.1 Flash 1017
- 83.2 GPT-6.1 Sol
- 81.9 Claude Opus 5
- 81.6 Claude Opus 5.5
- 81.4
Muse Spark 1.3
- 79.7 Claude Fable 5
- 78.9 GLM-5.3-Flash
- 77.6
Gemini 3.7 Flash
- 77.1 Grok 4.7
- 75.2 Claude Sonnet 5.5
- 73.2
Qwen 3.8 27B
- 71.7 Claude Sonnet 5
- 69.0
Gemini 3.1 Pro
- 68.3 Kimi K3
- 59.2
Muse Glimmer
- 51.9
Gemma 4 31B IT
- 49.1
DeepSeek V4.1 Flash
- 20.6
Nemotron 3 Nano Omni 30B-A3B
- 1
Gemini 4 Argon medium 87.7%
- 2 GPT-6 Astra medium 84.3%
- 3
DeepSeek V4.1 Flash 1017 84.3%
- 4 GPT-6.1 Sol medium 83.2%
- 5 Claude Opus 5 medium 81.9%
- 6 Claude Opus 5.5 medium 81.6%
- 7
Muse Spark 1.3 medium 81.4%
- 8 Claude Fable 5 medium 79.7%
- 9 GLM-5.3-Flash 78.9%
- 10
Gemini 3.7 Flash medium 77.6%
- 11 Grok 4.7 medium 77.1%
- 12 Claude Sonnet 5.5 medium 75.2%
- 13
Qwen 3.8 27B 73.2%
- 14 Claude Sonnet 5 medium 71.7%
- 15
Gemini 3.1 Pro medium 69%
- 16 Kimi K3 68.3%
- 17
Muse Glimmer 59.2%
- 18
Gemma 4 31B IT 51.9%
- 19
DeepSeek V4.1 Flash 49.1%
- 20
Nemotron 3 Nano Omni 30B-A3B 20.6%
Source: ONESTRUCTION’s leaderboard
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 87.7% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 2 | GPT-6 Astra | 84.3% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 3 | | 84.3% | pi | Oct 2026 | ai.onestruction.com | Official leaderboard |
| 4 | GPT-6.1 Sol | 83.2% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 5 | Claude Opus 5 | 81.9% | medium, pi | Jul 2026 | ai.onestruction.com | Official leaderboard |
| 6 | Claude Opus 5.5 | 81.6% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 7 | | 81.4% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 8 | Claude Fable 5 | 79.7% | medium, pi | Jun 2026 | ai.onestruction.com | Official leaderboard |
| 9 | GLM-5.3-Flash | 78.9% | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 10 | | 77.6% | medium, pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 11 | Grok 4.7 | 77.1% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 12 | Claude Sonnet 5.5 | 75.2% | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 13 | | 73.2% | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 14 | Claude Sonnet 5 | 71.7% | medium, pi | Jun 2026 | ai.onestruction.com | Official leaderboard |
| 15 | | 69% | medium, pi | Feb 2026 | ai.onestruction.com | Official leaderboard |
| 16 | Kimi K3 | 68.3% | pi | Jul 2026 | ai.onestruction.com | Official leaderboard |
| 17 | | 59.2% | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 18 | | 51.9% | pi | Apr 2026 | ai.onestruction.com | Official leaderboard |
| 19 | | 49.1% | pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 20 | | 20.6% | pi | Apr 2026 | ai.onestruction.com | Official leaderboard |
The best score, 87.7%, costs $0.18 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at medium comes within 4.5 points of the best for $0.05 a task, 4 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: ONESTRUCTION’s leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| medium | pi | 87.7% | $0.18 | ||
| GPT-6 Astra | medium | pi | 84.3% | $0.24 | |
| pi | 84.3% | ||||
| GPT-6.1 Sol | medium | pi | 83.2% | $0.05 | |
| Claude Opus 5 | medium | pi | 81.9% | $0.49 | |
| Claude Opus 5.5 | medium | pi | 81.6% | $0.14 | |
| medium | pi | 81.4% | $0.50 | ||
| Claude Fable 5 | medium | pi | 79.7% | $0.38 | |
| GLM-5.3-Flash | pi | 78.9% | |||
| medium | pi | 77.6% | $0.11 | ||
| Grok 4.7 | medium | pi | 77.1% | $0.26 | |
| Claude Sonnet 5.5 | medium | pi | 75.2% | $0.05 | |
| pi | 73.2% | ||||
| Claude Sonnet 5 | medium | pi | 71.7% | $0.35 | |
| medium | pi | 69% | $0.12 | ||
| Kimi K3 | pi | 68.3% | |||
| pi | 59.2% | ||||
| pi | 51.9% | ||||
| pi | 49.1% | ||||
| pi | 20.6% |
5 models have held number one on ONESTRUCTION’s leaderboard since its release in June 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: ONESTRUCTION’s leaderboard
Gemini 4 Argon on the official leaderboard passed 85% in September 2026
That was 4 months after its release. By the same age, 24% of the benchmarks from 2026 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: ONESTRUCTION’s leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Engineering and CAD
- EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge.
Gemini 4 Carbon 83.9%
- 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity.
LongCat-2.5 55.4%
- CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
- PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
- Razavi-Bench Not in model cards Models explain what happens in analog circuits and why. A language model awards up to four points per answer against a reference and a rubric.
Gemini 4 Carbon 98.3%
- CircuitRubric Not in model cards Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits. Claude Opus 4.8 96%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (20 entries).
- Pass Models scored 20 models we track.
- Pass Newest score The newest is from October 2026, for DeepSeek V4.1 Flash 1017.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Saturated. The best is 87.7%, past 85% since September 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on ONESTRUCTION: 20 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.