Trunk Tools
In-house benchmark · November 2026

Cortex vs. frontier AI models on real construction drawings

One test: 118 real plan sheets, read by Cortex and six models from OpenAI, Google and Anthropic.

97%
of what Cortex flags is right
Best frontier model, GPT 6.1 Terra: 79%
96%
of the objects on a sheet, found
Best frontier model, Claude Fable 5.2: 73%
<$0.01
to read one sheet on Cortex
Frontier models: $3.25 to $33.67 for the same sheet

The whole test

More accurate, and far cheaper

Each point is one system: how accurate it was, against what it cost to read one sheet. Cortex sits alone in the top-left corner. The six frontier models cluster lower and well to the right.

Accuracy against cost to read one sheet

Up is more accurate. Left is cheaper. Cost is on a log scale: each step is ten times the last.

  1. SystemScoreCost
  2. Cortex0.97<$0.01
  3. 1GPT 6.1 Terra0.72$3.25
  4. 2Gemini 4 Argon0.72$3.78
  5. 3Gemini 4 Carbon0.75$4.63
  6. 4GPT 6.1 Sol0.68$9.41
  7. 5GPT 6.2 Astra0.69$24.00
  8. 6Claude Fable 5.20.72$33.67

Accuracy

How much each system got right

The combined accuracy score balances two things: how much of what a system flags is right, and how much of what is on the sheet it finds. Cortex scored 0.97. The best frontier model, Gemini 4 Carbon, scored 0.75.

Accuracy finding objects on a drawing

Combined accuracy score, 0 to 1. Higher is better.

  1. Cortex0.97
  2. Gemini 4 Carbon0.75
  3. Gemini 4 Argon0.72
  4. GPT 6.1 Terra0.72
  5. Claude Fable 5.20.72
  6. GPT 6.2 Astra0.69
  7. GPT 6.1 Sol0.68

Why the gap exists

Drawings are read in small symbols

Much of what a drawing says is in marks a few pixels wide. The frontier models found most of the large object tags, few of the small ones, and none of the 461 smallest. Cortex found 95% of object tags across every size.

Share of object tags found, by size on the sheet

Tag size is its shorter side on a sheet rendered 4,800 pixels wide. The darker bar is the lowest frontier model and the lighter bar the highest.

Frontier models, lowest to highestCortex, all tag sizes: 95%
  1. Large tagsover 20 pixels86 to 90%
  2. Small tags11 to 20 pixels9 to 29%
  3. Smallest tagsunder 10 pixels0 of 461

Cost to read one sheet

Hundreds of times cheaper to run

A frontier model reads a sheet in pieces: about 35 enlarged tiles, then a second look at every object it flags, repeated for each object type. Cortex reads the sheet once. All eleven object types cost <$0.01 a sheet on Cortex, $3.25 on the cheapest frontier model and $33.67 on the most expensive. Model costs are measured usage at list prices, November 2026.

Cost to read one sheet for all eleven object types

Bars are drawn to scale, so Cortex is the dot at the start of the axis.

Per sheetvs Cortex
  1. Cortex<$0.011×
  2. GPT 6.1 Terra$3.25450×+
  3. Gemini 4 Argon$3.78520×+
  4. Gemini 4 Carbon$4.63640×+
  5. GPT 6.1 Sol$9.411,300×+
  6. GPT 6.2 Astra$24.003,330×+
  7. Claude Fable 5.2$33.674,670×+

Maximum shown is $33.67 per sheet.

On a sheet

The eleven object types we tested

Pick an object type to see where it appears on a plan, and how Cortex scored on it against the best of the six frontier models.

301 OFFICE302 OFFICE303 CONFERENCE304 RESTROOM305 OPEN OFFICE306 ELECTRICALSTAIR 2L3AABCDE1234SSSSSSSS301302303304305306307308TRUNK PROJECTLEVEL 3 FLOOR PLANSHEETA-201ILLUSTRATIVE SHEET · NOT A CUSTOMER DRAWING

Object type 01 / 11

Doors

9 on this sheet, each one bracketed.

Cortex0.98
Best frontier model0.85

+0.13 Cortex lead on doors.

Combined accuracy score, 0 to 1, from the in-house benchmark, November 2026. The sheet is an illustration.

The sheet is an illustration, not one of the 118 test sheets.

The numbers

Every result, in two tables

Trunk Tools in-house benchmark, November 2026: eleven object types on 118 real plan sheets.

Reading drawings: accuracy and cost, by system

Combined accuracy score and cost to read one sheet, for Cortex and six frontier models
SystemCombined accuracy scoreCost per sheetvs Cortex
Cortex0.97<$0.011×
Gemini 4 Carbon0.75$4.63640×+
Gemini 4 Argon0.72$3.78520×+
GPT 6.1 Terra0.72$3.25450×+
Claude Fable 5.20.72$33.674,670×+
GPT 6.2 Astra0.69$24.003,330×+
GPT 6.1 Sol0.68$9.411,300×+

Combined accuracy score, by object type

Combined accuracy score by object type: Cortex against the best frontier model on that type
Object typeCortexBest frontier modelCortex lead
Windows0.970.66+0.31
Sprinklers0.940.67+0.27
Lighting fixtures0.930.70+0.23
Switches0.980.76+0.22
Object tags0.970.75+0.22
Receptacles0.950.74+0.21
Columns0.950.78+0.17
Air terminals0.940.77+0.17
Doors0.980.85+0.13
Toilets0.990.94+0.05
Grid line markers1.000.99+0.01

Beyond one sheet

A project is thousands of documents, not one

Take a project with 10,000 documents averaging 5 pages each. At about 500 tokens a page, that is roughly 25 million tokens of text, more than a general model takes in one conversation. So someone has to choose which documents to hand it, for every question.

Give a general model the right three documents and it will answer well. Your project has 10,000, and knowing which three is the job.

Cortex reads the whole project once, drawings included, and keeps what it read. Every question after that searches all of it.

This section is an illustration worked from round numbers, not a test result. Everything above it was measured.

Method

How the test was run

  1. 01

    Same sheets for everyone

    118 real plan sheets with 25,483 hand-labelled objects across 11 object types. None were used to tune any system.

  2. 02

    Frontier models given a fair run

    Each sheet was cut into overlapping tiles and enlarged so small symbols were legible. Every candidate was then shown back to the same model to confirm or reject, which roughly doubled their scores. Prompts were tuned on one model and reused unchanged for the rest.

  3. 03

    A strict definition of a hit

    A detection counted only if its box overlapped the true object by at least half. Precision is how often a flagged object was right; recall is how many real objects were found.

  4. 04

    Costs at list price

    Model costs use measured usage at published list prices in November 2026. Cortex's cost is the measured computing cost of reading one sheet, with the system running at full load.

This is our own test, not an independent one. It covers eleven object types that Cortex reads in production at a score of 0.93 or better, and it measures one task: finding objects on a plan sheet. We run it again as new models are released and update this page when the results change.

These are excellent general-purpose models, and they keep improving. In this test they came within 0.01 of Cortex on grid line markers and scored 0.94 on toilets and 0.85 on doors. A model tuned by its own maker for this task might score higher than it did here.

FAQ

Questions about the benchmark

Partly. In Trunk Tools' in-house benchmark (November 2026, 118 real plan sheets), six frontier models from OpenAI, Google and Anthropic scored 0.68 to 0.75 on combined accuracy at finding objects on a sheet. The best was 79% precise and the best found 73% of the objects. They did well on large, distinct symbols such as grid line markers and missed many small ones. Cortex scored 0.97 on the same sheets.

Cortex, the Trunk Tools AI layer, was 97% precise and found 96% of the objects on 118 real plan sheets, across 11 object types and 25,483 hand-labelled objects. This is an in-house test run in November 2026.

Much of what a drawing says is in symbols a few pixels wide. In this test the frontier models found 86 to 90% of large object tags, 9 to 29% of small ones, and none of the 461 smallest. Cortex found 95% of object tags across every size.

Reading all 11 object types on one sheet cost <$0.01 on Cortex. The same sheet cost $3.25 on the cheapest frontier model tested and $33.67 on the most expensive, at published list prices in November 2026. A frontier model reads a sheet as about 35 enlarged tiles and then checks each object it flags. Cortex reads the sheet once.

Six current frontier models: Gemini 4 Carbon, Gemini 4 Argon, GPT 6.1 Terra, Claude Fable 5.2, GPT 6.2 Astra, GPT 6.1 Sol. Each one read the same 118 sheets through the same method, with prompts tuned on one model and reused unchanged for the rest.

One task: finding objects on a plan sheet. It covered 11 object types: doors, windows, grid line markers, toilets, switches, object tags, columns, receptacles, air terminals, sprinklers, lighting fixtures. A detection counted only if its box overlapped the true object by at least half. The results say nothing about how these models perform on other tasks.

No. It is Trunk Tools' own test, run in November 2026. None of the 118 sheets were used to tune any system, and the method is published on this page. A model tuned by its own maker for this task might score higher than it did here. We run the test again as new models are released and update the page when the results change.

Let builders build

See Cortex read your drawings

Bring a drawing set to the demo and we'll run it live.

Book your demo

See Trunk Tools live on actual project data