GPT-6 Astra tops robot index, but finishes dual-arm sim task only twice in 800 trials
minchoi · x · 2026-11-03
minchoi rounds up two robot-intelligence benchmarks:
- Playground's Robot Intelligence Index (16 public benchmarks): OpenAI's GPT-6 Astra ranks #1 overall at 1905, with coding agents and world action models filling the top 10 (InternW0-Δ 1828, GPT-6.1 Sol 1808, Gemini 4 Argon 1797).
- micro1's Dual-Arm Sim: 10 frontier models, 800 trials, only 11 completions — Gemini 4 Argon finished 9 times, Astra twice, tied at 49.5%. Models claimed "task complete" 213 times; every claim was wrong.
Takeaway: general models now lead the robot-brain race, but knowing when the job is actually done remains unsolved.
More from Embodied
- NVIDIA's LucidLyra turns a single image into queryable 3D Gaussian scenes — CSProfKGD · 2026-11-03
- YC-backed Cyclon ships AI phone OS on Pixel 8a, promising apps that act for you — Scobleizer · 2026-11-03
- YC-backed Subvocal builds RF smart glasses that decode silent speech into text — aarushyadav · 2026-11-03
- Starcloud-1 marks one year in orbit with the only NVIDIA H100 in space, 3 more launches planned — ycombinator · 2026-11-03
- Ant Group's Robbyant shows LingBot-VLA 2.0: 60k hours of real data, runs on 20+ robots — huangyun_122 · 2026-11-03
- Ropedia W0: cross-embodiment world model trained on 10k hours of human video hits SOTA — liuziwei7 · 2026-11-03