Surgical robot sim benchmark: only 2 of 10 frontier models completed task, all 213 success claims wrong
Exp_Mark · x · 2026-10-31
micro1 released Dual-Arm Sim, a new robotics benchmark giving 10 frontier models control of a surgical robot in a simulated operating room.
- Across 800 trials, only two models completed the task at all: Gemini 4 Argon nine times and GPT-6 Astra twice
- Models claimed success 213 times; every claim was wrong, and in 94 of them the robot never touched the object
- The benchmark exposes a large gap between models' self-reported success and actual embodiment control
More from Embodied
- Subvocal, a 3-person YC startup, raises $1.3M for glasses that read silent speech at 200+ wpm — garrytan · 2026-10-31
- She hacked her doorbell camera to rank Halloween costumes — and open-sourced it — jeff_weinstein · 2026-10-31
- China adds embodied AI robot technician and digital twin engineer to official jobs list — nordicinst · 2026-10-31
- YC-backed Axonnic launches EMG sleeve to capture human hand skills for robot training — ycombinator · 2026-10-31
- VITURE launches $599 Phantom Beast XR glasses in Phantom Blade Zero collab — Scobleizer · 2026-10-31
- Agility Robotics lost $138.1M in 2025 as Brett Adcock's doom prediction nears — Rewkang · 2026-10-31