Construction AI Leaderboard
Models answer construction questions, inspect drawings, edit building models, and generate validation rules. ONESTRUCTION averages the representative scores from five evaluations.
ONESTRUCTION runs each model once per benchmark. Its BIM editing grader and turn limit differ from the original protocol.
- Made by
- ONESTRUCTION
- Released
- November 2026
- Kind
- Composite indices
- 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
- Another benchmark
- Refresh
- One fixed set
- Run by
- A host
- 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
Claude Opus 5.5 leads with 73.7
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 73.7 Claude Opus 5.5
- 73.6
Gemini 4 Argon
- 72.7 Claude Opus 5
- 70.2 Claude Fable 5
- 70.2 GPT-6.1 Sol
- 70.1 GPT-6 Astra
- 68.7 Grok 4.7
- 67.2
Muse Spark 1.3
- 66.9 Claude Sonnet 5.5
- 66.7
DeepSeek V4.1 Flash 1017
- 66.5
Gemini 3.7 Flash
- 65.7 Kimi K3
- 64.2 GLM-5.3-Flash
- 61.2 Claude Sonnet 5
- 59.4
DeepSeek V4.1 Flash
- 59.2
Gemini 3.1 Pro
- 58.1
Qwen 3.8 27B
- 49.6
Muse Glimmer
- 40.8
Gemma 4 31B IT
- 26.5
Nemotron 3 Nano Omni 30B-A3B
- 1 Claude Opus 5.5 medium 73.7
- 2
Gemini 4 Argon medium 73.6
- 3 Claude Opus 5 medium 72.7
- 4 Claude Fable 5 medium 70.2
- 5 GPT-6.1 Sol medium 70.2
- 6 GPT-6 Astra medium 70.1
- 7 Grok 4.7 medium 68.7
- 8
Muse Spark 1.3 medium 67.2
- 9 Claude Sonnet 5.5 medium 66.9
- 10
DeepSeek V4.1 Flash 1017 66.7
- 11
Gemini 3.7 Flash medium 66.5
- 12 Kimi K3 65.7
- 13 GLM-5.3-Flash 64.2
- 14 Claude Sonnet 5 medium 61.2
- 15
DeepSeek V4.1 Flash 59.4
- 16
Gemini 3.1 Pro medium 59.2
- 17
Qwen 3.8 27B 58.1
- 18
Muse Glimmer 49.6
- 19
Gemma 4 31B IT 40.8
- 20
Nemotron 3 Nano Omni 30B-A3B 26.5
Source: Official Construction AI Leaderboard leaderboard
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 73.7 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 2 | | 73.6 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 3 | Claude Opus 5 | 72.7 | medium, pi | Jul 2026 | ai.onestruction.com | Official leaderboard |
| 4 | Claude Fable 5 | 70.2 | medium, pi | Jun 2026 | ai.onestruction.com | Official leaderboard |
| 5 | GPT-6.1 Sol | 70.2 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 6 | GPT-6 Astra | 70.1 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 7 | Grok 4.7 | 68.7 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 8 | | 67.2 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 9 | Claude Sonnet 5.5 | 66.9 | medium, pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 10 | | 66.7 | pi | Oct 2026 | ai.onestruction.com | Official leaderboard |
| 11 | | 66.5 | medium, pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 12 | Kimi K3 | 65.7 | pi | Jul 2026 | ai.onestruction.com | Official leaderboard |
| 13 | GLM-5.3-Flash | 64.2 | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 14 | Claude Sonnet 5 | 61.2 | medium, pi | Jun 2026 | ai.onestruction.com | Official leaderboard |
| 15 | | 59.4 | pi | Sep 2026 | ai.onestruction.com | Official leaderboard |
| 16 | | 59.2 | medium, pi | Feb 2026 | ai.onestruction.com | Official leaderboard |
| 17 | | 58.1 | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 18 | | 49.6 | pi | Aug 2026 | ai.onestruction.com | Official leaderboard |
| 19 | | 40.8 | pi | Apr 2026 | ai.onestruction.com | Official leaderboard |
| 20 | | 26.5 | pi | Apr 2026 | ai.onestruction.com | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as IDS generation, Drawings & documents and BIM understanding. Claude Opus 5.5 leads 2 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
IDS generation
20 models we track have a score here.
- 1 Claude Opus 5.5 63.0
- 2
Gemini 4 Argon 61.9
- 3 GPT-6 Astra ↑3 61.7
- 4 Claude Opus 5 ↓1 60.9
- 5 GPT-6.1 Sol 60.7
- 6 Claude Sonnet 5.5 ↑3 60.0
- 7 Claude Fable 5 ↓3 58.6
- 8 Grok 4.7 ↓1 58.2
- 9
Gemini 3.7 Flash ↑2 52.5
- 10
Gemini 3.1 Pro ↑6 50.1
Drawings & documents
20 models we track have a score here.
- 1 Claude Opus 5.5 70.2
- 2
DeepSeek V4.1 Flash 1017 ↑8 67.6
- 3 GPT-6.1 Sol ↑2 66.3
- 4 GPT-6 Astra ↑2 66.2
- 5
Gemini 4 Argon ↓3 65.3
- 6 Claude Fable 5 ↓2 64.6
- 7
DeepSeek V4.1 Flash ↑8 64.1
- 8 Kimi K3 ↑4 63.5
- 9 Claude Opus 5 ↓6 63.3
- 10 GLM-5.3-Flash ↑3 61.9
BIM understanding
20 models we track have a score here.
- 1 Claude Opus 5 ↑2 65.8
- 2 Claude Opus 5.5 ↓1 60.5
- 3
Gemini 4 Argon ↓1 59.1
- 4 Kimi K3 ↑8 58.6
- 5
Muse Spark 1.3 ↑3 57.8
- 6 Claude Fable 5 ↓2 54.7
- 7 Claude Sonnet 5.5 ↑2 54.7
- 8 Grok 4.7 ↓1 54.3
- 9 GLM-5.3-Flash ↑4 51.8
- 10
Gemini 3.7 Flash ↑1 51.6
BIM editing
20 models we track have a score here.
- 1
Gemini 4 Argon ↑1 87.7
- 2 GPT-6 Astra ↑4 84.3
- 3
DeepSeek V4.1 Flash 1017 ↑7 84.3
- 4 GPT-6.1 Sol ↑1 83.2
- 5 Claude Opus 5 ↓2 81.9
- 6 Claude Opus 5.5 ↓5 81.6
- 7
Muse Spark 1.3 ↑1 81.4
- 8 Claude Fable 5 ↓4 79.7
- 9 GLM-5.3-Flash ↑4 78.9
- 10
Gemini 3.7 Flash ↑1 77.6
Cost estimation QA
20 models we track have a score here.
- 1
Gemini 3.7 Flash ↑10 95.5
- 2
Gemini 4 Argon 94.0
- 3
Gemini 3.1 Pro ↑13 93.3
- 4 Claude Fable 5 93.3
- 5 Grok 4.7 ↑2 93.3
- 6 Claude Opus 5.5 ↓5 93.3
- 7 GPT-6.1 Sol ↓2 93.3
- 8
Muse Spark 1.3 92.5
- 9 Kimi K3 ↑3 91.8
- 10 Claude Opus 5 ↓7 91.8
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Construction AI Leaderboard leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Construction AI Leaderboard 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 Other
- Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Claude Fable 5.2 64.6
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- Vals Science Index In use Agents are scored on the equal average of BioMysteryBench, MysteryMechanism and Terminal-Bench-Science. GPT-6.2 Astra 68.4%
- Decision Index Public v0.3 In use Decision models return probabilities over labeled options in public tasks covering knowledge, language, retrieval, tools, and arts. A chance-corrected weighted aggregate combines the task scores. Granite Switch 4.1 30B 51.3
- SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
- MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities.
Qwen3-Embedding-8B 72.2%
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 Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on ai.onestruction.com: 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.