← Leaderboard

GEN-1.5

VLA
Generalist AI · Aug 19, 2026

GEN-1 successor that learns new tasks in context from about 30 seconds of video and outputs actions at 100 Hz. Results are self-reported on 10 short-horizon tasks: 59% average success with one-shot prompting and 83% after 10 gradient steps on 5 minutes of data per task.

Type
VLA
Parameters
—
Backbone
–
Weights
Closed
License
–
Commercial use
Unclear
Released
Aug 19, 2026
Robots
–
SO-101
–
LeRobot
–
Inputs
–
VRAM
–

Benchmark results

0 of 13 benchmarks

No benchmark results recorded yet.

Not reported on 13 benchmarks
Wrong or missing number? Report an error