Project AURIONAI Use-Cases Research & Innovation
Figure AI

Figure unseen-homes whole-task evaluation

Vendor whole-task completion rate in unseen homes

world models and roboticsstatic
1scores
1models
0independent
0maintainer-run
1vendor-reported

Definition

Version
not in the notes
Category
world models and robotics
Maintainer
Figure AI
Status
static
Home page
not in the notes

Sources

  1. aiwiki.ai/wiki/helix_vla https://aiwiki.ai/wiki/helix_vla

Scores

1 of 1 scores shown figure-unseen-homes-eval-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
Figure AIHelix 2.556 %vendor-reportedWhole-task completion in unseen homesVendor (via aiwiki)Sep 2026aiwiki.ai
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Figure Unseen-Homes Whole-Task Evaluation", https://aurion.semai.id/benchmarks/figure-unseen-homes-eval/, records of October 2026.