Benchmark Almanac

AEC-Geometric-Bench

Kamai 0.93 tops its leaderboard Gemini 3.7 Flash 0.06 leads the models we track
Not in model cards

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
Language
English
In and out
Documents → Images
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 5 models we track

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:

  1. 1 Kamai 0.93
  2. 2 Gemini 3.7 Flash 0.06
  3. 3 Claude Opus 5 0.05
  4. 4 Claude Fable 5 0.04
  5. 5 Gemini 3.1 Pro 0.02
  6. 6 GPT-5.6 Sol 0.01

Source: Official AEC-Geometric-Bench leaderboard

#EntryScoreSettingDateSource
1 Kamai 0.93 Official leaderboard
2 Gemini 3.7 Flash 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 Gemini 3.1 Pro 0.02 Feb 2026 Official leaderboard
6 GPT-5.6 Sol 0.01 Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.7 Flash 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 Gemini 3.1 Pro 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. 1 Claude Opus 5 ↑1 0.27
  2. 2 Gemini 3.7 Flash ↓1 0.27
  3. 3 Claude Fable 5 0.25
  4. 4 Gemini 3.1 Pro 0.16
  5. 5 GPT-5.6 Sol 0.07

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.

Anthropic Google DeepMind
Own leaderboard Not tested since Aug 2026

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.02 0.04 0.06 2026 0.02 0.04 0.06 2026

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

All 636 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.

How we check