No true general-purpose robotics model yet: general AI agents vs VLA models tied across 901 head-to-head runs
DJiafei · x · 2026-11-07
Chris Paxton highlights a robotics benchmark: there's still no true general-purpose robotics model, not even from OpenAI. Across 901 head-to-head comparisons, general-purpose AI agents made more progress than robot-specific VLA models in 394 runs, VLA led in 265, and 242 were ties — with high variance, so no one-size-fits-all winner. General AI can now compete with specialized VLAs, but a true general robotics model remains unsolved.
More from Embodied
- Tsinghua's ParallelWorld uses test-time scaling for embodied agents, lifting success 56% to 83% — jiqizhixin · 2026-11-07
- Realbotix Echo robots cost $11,950-$59,950: selling a humanlike interface, bodies as upgrades — TansuYegen · 2026-11-07
- Autonomous factory trains robots in 4 weeks to bend wires and screws, lands 3-year production contract — Scobleizer · 2026-11-07
- 3D tactile imaging demo at CoRL: Technion team shows artificial touch work — AvivTamar1 · 2026-11-07
- Scottish hospital unveils world's first dedicated pediatric surgical robot — Polymarket · 2026-11-07
- X Square says its robot is fine, powered by embodied AI model WALL-B — Scobleizer · 2026-11-07