SenseTime-led study benchmarks GPT-6-Astra embodied intelligence: high scores, hard reality

A SenseTime-led team published the largest empirical study of GPT-6-Astra's embodied intelligence, spanning 12 simulation benchmarks and 8 real robot platforms with an open-sourced framework. Scores near saturation, but real-world costs and limitations hinder deployment.

2026-10-22 ~ 2026-10-22 · 2 related posts

• GPT-6-Astra nears saturation on 12 robot benchmarks but burns 9M tokens per task — rohanpaul_ai · 2026-10-22
• SenseTime's 12-benchmark study: GPT-6-Astra hits SOTA in sim but costs ~$55 to place pens — heyshrutimishra · 2026-10-22