Updated November 17, 2026
Each model at its highest-rated thinking level · Higher is better
The takeoff rating is out of 100: accuracy contributes 50 points, cost 25 and speed 25.
For each drawing, we estimate how long the takeoff would take by hand and use an hourly labor rate to estimate its cost. Each thinking level is rated separately against those estimates.
We estimate an average of 30 minutes of manual work per test across the 4 selected tests, costing 1,916 credits ($19.16) at an estimator wage of $38 per hour.
Time matters because when you use AI for a takeoff, you work alongside the model: reviewing its work, requesting corrections and waiting for each response. For unattended takeoffs, you may prefer to prioritize accuracy and cost.
The tags mark the leaders among models scoring 85% or more: Most accurate for the highest score, Best value for the most accuracy per credit, and Best speed for the most accuracy per minute.
Score at each model’s most accurate level · Higher is better
Minutes at each model’s most accurate level · Lower is better
Credits at each model’s most accurate level · Lower is better
Score per credit at each model’s most accurate level · Higher is better
Score per minute at each model’s most accurate level · Higher is better
Score against credits per takeoff for every level each model ran. Cost runs on a log scale, and score on one that spreads out high scores. A line joins one model's levels. Up and to the left is better.
The effect of more thinking varies by model. Sometimes it buys a small accuracy gain at a much higher cost in time and money. Other models become faster or cheaper at higher thinking levels. Compare the results for each model rather than assuming a lower setting is more efficient.
We test AI models on construction PDFs: measuring floor areas and counting doors, windows and electrical devices.
We compare each result with an answer key and combine accuracy, cost and time into a takeoff rating out of 100.
Claude Fable 5.2 leads on accuracy. Terra 6.1 has the highest overall rating when cost and speed are included.
Each test includes a real construction drawing, a takeoff request and an answer key.
We test models at different thinking levels and record:
Valid alternatives are accepted: a stair area can be counted on either floor it connects, but only once.
Each test has equal weight. Repeated runs are averaged within each test; results from older test versions are excluded.
These results cover 4 drawing tests using Deta’s takeoff tools. Performance can vary with other drawings, prompts and tools. Manual times are estimates, not timed human trials.
Read the benchmark findings and see example drawingsUse the overall rating as a starting point. If accuracy matters most, compare the accuracy scores directly. For unattended work, cost may matter more than speed. Check the results for the type of takeoff you need, and review the finished markups.
Deta’s model picker shows the takeoff rating for each thinking level, alongside accuracy, cost and speed, so you can use these results when choosing a model.
Rows show each model’s most accurate level, prioritizing levels with more completed tests. Expand a row to compare thinking levels.
| Model | Level | Score | Tests | Runs | Duration | Credits | By test |
|---|---|---|---|---|---|---|---|
Claude Fable 5.2Most accurate | Low | 99.7% | 4/4 | 4 | 38m 45s | 1458 | Area_Complex_1 99.5% · Area_Simple_1 99.3% · Electrical_Simple_1 100% · Opening_Simple_1 100% |
Astra 6 | High | 99.6% | 4/4 | 4 | 9m 25s | 554 | Electrical_Simple_1 100% · Opening_Simple_1 100% · Area_Complex_1 98.4% · Area_Simple_1 99.9% |
Sol 6.1Best speed | High | 99.3% | 4/4 | 4 | 7m 21s | 77 | Electrical_Simple_1 99.6% · Area_Simple_1 99.7% · Opening_Simple_1 100% · Area_Complex_1 97.9% |
Terra 6.1 | Maximum | 99.3% | 4/4 | 4 | 17m 25s | 103 | Area_Complex_1 97.2% · Opening_Simple_1 100% · Electrical_Simple_1 100% · Area_Simple_1 99.8% |
Gemini 4 Carbon | High | 99.3% | 4/4 | 4 | 52m 33s | 494 | Area_Complex_1 97.2% · Electrical_Simple_1 100% · Area_Simple_1 99.8% · Opening_Simple_1 100% |
Gemini 4 Argon | High | 98.6% | 4/4 | 4 | 37m 23s | 393 | Opening_Simple_1 100% · Electrical_Simple_1 100% · Area_Simple_1 98.9% · Area_Complex_1 95.6% |
Claude Opus 5.5 | High | 95.3% | 4/4 | 4 | 19m 22s | 352 | Opening_Simple_1 100% · Area_Simple_1 95.9% · Electrical_Simple_1 92.2% · Area_Complex_1 93% |
Claude Sonnet 5.5 | Medium | 94.4% | 4/4 | 4 | 44m 51s | 448 | Opening_Simple_1 100% · Area_Complex_1 88.7% · Area_Simple_1 96.8% · Electrical_Simple_1 92% |
Kimi K3.1 Pro | High | 92% | 4/4 | 4 | 11m 51s | 132 | Area_Complex_1 78.5% · Electrical_Simple_1 96.6% · Area_Simple_1 92.8% · Opening_Simple_1 100% |
Qwen4 Max | High | 89.7% | 4/4 | 4 | 35m 35s | 156 | Area_Complex_1 88.6% · Electrical_Simple_1 99.6% · Opening_Simple_1 75% · Area_Simple_1 95.6% |
Luna 6Best value | Maximum | 88.6% | 4/4 | 4 | 26m 38s | 22 | Electrical_Simple_1 97.3% · Area_Simple_1 95.7% · Opening_Simple_1 75% · Area_Complex_1 86.2% |
Gemini 3.8 Flash | Low | 87% | 4/4 | 4 | 17m 10s | 237 | Area_Simple_1 98.7% · Area_Complex_1 64.6% · Opening_Simple_1 95% · Electrical_Simple_1 89.7% |
GLM 5.3 FlashX | Low | 83.7% | 4/4 | 4 | 16m 54s | 99 | Area_Simple_1 86.4% · Electrical_Simple_1 81.1% · Opening_Simple_1 92.7% · Area_Complex_1 74.4% |
DeepSeek V4.1 Flash | High | 80.1% | 4/4 | 4 | 13m 08s | 15 | Area_Complex_1 67.9% · Opening_Simple_1 68.3% · Area_Simple_1 91.6% · Electrical_Simple_1 92.6% |
Claude Haiku 5.5 | Low | 70.8% | 4/4 | 4 | 7m 59s | 9 | Area_Complex_1 61.5% · Area_Simple_1 86.9% · Electrical_Simple_1 73.5% · Opening_Simple_1 61.1% |