gpt-6VIDEO
GPT-6 Astra tops Gemini 3.8 Flash and Fable 5.1 on real-world robot tasks
GPT-6 Astra, Gemini 3.8 Flash, and Fable 5.1 were compared on two real-world robot tasks, fitting a pipette tip and loading a microwave, and Astra scored highest on both.
CortexAI
@cortexairobotArchived 2026.09.18Originally posted 2026.09.18
CortexAI @cortexairobotOriginally posted 2026.09.18
We tested GPT-6 Astra, Gemini 3.8 Flash, and Fable 5.1 on two real-world robot tasks from our MolmoAct2 real-world evaluations: 1. Fitting a 5 mm pipette tip 2. Loading a microwave Astra scored highest on both. 🥇 Here are some few surprising things that Astra did to come out on top. 🧵
x.com/cortexairobot/status/2100628691114201489Archived 2026.09.18 10:09