AEC-Geometric-Bench
Models locate doors, windows, and fixtures on construction drawings and trace walls and enclosed spaces. The scorer matches objects and compares wall and area masks.
Kamai publishes five general-purpose model scores alongside its production system on 312 sheets, including 15 public sheets. OpenTakeoff independently scored one released sheet.
- Made by
- Kamai
- Released
- August 2026
- Kind
- Documents, charts and text in images
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Civil engineering
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Image, video and 3D generation
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
Kamai tops the leaderboard with 0.93 Gemini 3.7 Flash leads with 0.06 among models released by August 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 3.7 Flash, at 0.06. This view shows only models we track, each at its best.
The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 13 more
- 1 Kamai 0.93
- 2
Gemini 3.7 Flash 0.06
- 3 Claude Opus 5 0.05
- 4 Claude Fable 5 0.04
- 5
Gemini 3.1 Pro 0.02
- 6 GPT-5.6 Sol 0.01
Source: Official AEC-Geometric-Bench leaderboard
- 1
Gemini 3.7 Flash 0.06
- 2 Claude Opus 5 0.05
- 3 Claude Fable 5 0.04
- 4
Gemini 3.1 Pro 0.02
- 5 GPT-5.6 Sol 0.01
Source: Official AEC-Geometric-Bench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Kamai | 0.93 | Official leaderboard | ||
| 2 | | 0.06 | Aug 2026 | Official leaderboard | |
| 3 | Claude Opus 5 | 0.05 | Jul 2026 | Official leaderboard | |
| 4 | Claude Fable 5 | 0.04 | Jun 2026 | Official leaderboard | |
| 5 | | 0.02 | Feb 2026 | Official leaderboard | |
| 6 | GPT-5.6 Sol | 0.01 | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 0.06 | Aug 2026 | Official leaderboard | |
| 2 | Claude Opus 5 | 0.05 | Jul 2026 | Official leaderboard | |
| 3 | Claude Fable 5 | 0.04 | Jun 2026 | Official leaderboard | |
| 4 | | 0.02 | Feb 2026 | Official leaderboard | |
| 5 | GPT-5.6 Sol | 0.01 | Jul 2026 | Official leaderboard |
Rankings by part
We read 7 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Wall pixel F1, Area pixel F1 and Area instance F1. Claude Opus 5 leads 3 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Wall pixel F1
5 models we track have a score here.
- 1 Claude Opus 5 ↑1 0.27
- 2
Gemini 3.7 Flash ↓1 0.27
- 3 Claude Fable 5 0.25
- 4
Gemini 3.1 Pro 0.16
- 5 GPT-5.6 Sol 0.07
Area pixel F1
5 models we track have a score here.
- 1
Gemini 3.7 Flash 0.80
- 2 GPT-5.6 Sol ↑3 0.79
- 3 Claude Opus 5 ↓1 0.76
- 4 Claude Fable 5 ↓1 0.76
- 5
Gemini 3.1 Pro ↓1 0.61
Area instance F1
5 models we track have a score here.
- 1 Claude Opus 5 ↑1 0.23
- 2 Claude Fable 5 ↑1 0.18
- 3 GPT-5.6 Sol ↑2 0.17
- 4
Gemini 3.1 Pro 0.13
- 5
Gemini 3.7 Flash ↓4 0.08
Object F1 on 15 released sheets
5 models we track have a score here.
- 1
Gemini 3.7 Flash 0.03
- 2 Claude Opus 5 0.02
- 3
Gemini 3.1 Pro ↑1 0.01
- 4 Claude Fable 5 ↓1 0.01
- 5 GPT-5.6 Sol 0.00
Wall pixel F1 on 15 released sheets
5 models we track have a score here.
- 1 Claude Fable 5 ↑2 0.29
- 2 Claude Opus 5 0.28
- 3
Gemini 3.7 Flash ↓2 0.24
- 4
Gemini 3.1 Pro 0.18
- 5 GPT-5.6 Sol 0.09
Area pixel F1 on 15 released sheets
5 models we track have a score here.
- 1
Gemini 3.7 Flash 0.80
- 2 Claude Opus 5 0.78
- 3 Claude Fable 5 0.78
- 4 GPT-5.6 Sol ↑1 0.74
- 5
Gemini 3.1 Pro ↓1 0.55
Area instance F1 on 15 released sheets
5 models we track have a score here.
- 1 Claude Opus 5 ↑1 0.23
- 2 Claude Fable 5 ↑1 0.19
- 3
Gemini 3.1 Pro ↑1 0.12
- 4 GPT-5.6 Sol ↑1 0.10
- 5
Gemini 3.7 Flash ↓4 0.08
2 models have held number one on the official leaderboard since its release in August 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AEC-Geometric-Bench 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 AEC-Geometric-Bench 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 Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (6 entries).
- Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from August 2026, for Gemini 3.7 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on kamai.io: 5 rows for models we track and 1 other entry 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.