S
SKY-001 (research preview)
Self-reportedSkyfall AI
Announced 19 Oct 2026, not released. An "Engineering World Model" that beats GPT-6 Astra and every frontier model its makers tested, on its makers' CAD and BIM tasks, in its makers' table.
Trust Me Bro Intelligence Indexn/aCannot be used, so cannot be measured
Self-reported"Beats every frontier model we tested"The number in the launch post
Benchmaxx Gap+∞Self-reported minus measured
Output speed—Tokens per second
Cost per task$0.005USD, TMB Index task average
Context window0kRemembers 0k of it
Days to ship8+Still counting
Evaluations
How SKY-001 scores on every benchmark
This model cannot be used, so values below are derived from public claims rather than measurement. Bars show where the score sits between the worst and best model on each benchmark. Rank 1 is best, whatever "best" means for that benchmark.
Incident database
Filed incidents
In the wild
What people posted
Real posts, quoted verbatim. The scores on this page are not real; these are.
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18
♥ 16.3KOpen on X ↗
We launched the first Engineering World Model, SKY-001, this week and it already outperforms all the frontier LLMs in CAD and BIM in speed, cost and precision.
Here’s an example of how our model compares to OpenAI’s Astra, Anthropic’s Fable 5.1 and Google’s Gemini 4.
These
♥ 1KOpen on X ↗
Compare