AIToday
Large Language ModelsAI Coding AssistantsOpen-Source AIAI WeeklyPublished: Nov 19, 2026, 01:00 JST

CADMAGEDDON on Qwen3.8-27B beats frontier CAD models across five benchmarks

Send on LINE
CADMAGEDDON on Qwen3.8-27B beats frontier CAD models across five benchmarks

3 Key Points

  1. What happened

    CADMAGEDDON scores 0.991 on BenchCAD's 64³ voxel IoU over a 1000-part subset, above vendor-reported 0.963, 0.962 and 0.959 for Claude Sonnet 5.5, Claude Opus 5.5 and GPT-6 Astra.

  2. Why it matters

    The margin suggests an open-weight model paired with geometric fitting tools can outperform frontier vendor entries on CAD reconstruction, though the paper notes inputs and subsets differ.

WHO IT HITSCAD engineers and mechanical design teams who convert scans or meshes into editable CAD models may find an open-source, single-GPU option competitive with frontier-model services, though the method so far handles only clean single-part meshes.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

CADMAGEDDON arrives from a collaboration of Lomonosov Moscow State University, Innopolis University and FusionBrain Lab, and its design choice is the story: rather than asking a single large model to output geometry end to end, it splits each feature into a structural decision made by a vision-language model and numerical values supplied by geometric fitting. Algorithmic instruments detect planes, cross-sections, hole stacks, lines and arcs, name them, and let the agent compose features by reference. The authors conclude that "the instruments, not model scale, carry much of the accuracy" — a claim supported by their finding that the same Qwen3.8-27B wrapped in a general-purpose Qwen Code harness scores only 0.790 on Task 3 of BenchCAD-2 and returns no prediction on 2 of the 23 parts, versus 0.933 with CadQuery output for CADMAGEDDON.

The benchmark picture places that design against frontier vendors. On BenchCAD's 64³ voxel IoU, CADMAGEDDON's 0.991 on a 1000-part subset sits above vendor-reported 0.963, 0.962 and 0.959 for Claude Sonnet 5.5, Claude Opus 5.5 and GPT-6 Astra, though the authors note inputs and subsets differ. On MCB, IoU rises from CADFather's 0.862 to 0.933 and GMS from 0.705 to 0.818 under the same evaluation; on CADENA-Bench, GMS jumps from 0.800 to 0.909. The limits are stated plainly: clean single-part meshes only, CAD-derived benchmarks, and up to 30 or 60 model calls with long contexts per reconstruction — slower than single-pass learned models. Code is on GitHub, and the paper lands the same day as separate Qwen3.8-27B agent work.

FAQ
How does CADMAGEDDON split the CAD reconstruction task?
A vision-language model chooses each feature's structure among named geometric entities, while geometric fitting supplies the numerical values.
What does CADMAGEDDON cost per part?
The paper reports $1.05 per part on OpenRouter pricing for Task 3 of BenchCAD-2.
What are the main limitations of CADMAGEDDON?
It assumes a clean mesh of a single part; benchmarks are all CAD-derived, so real scans and assemblies are deferred. On BenchCAD-2, every attempt misses the 0.7 mm walls of one part and builds at most two of the 51 through-holes of another.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMIT Technology Review's AI Hype Index: AI is everywhere