A 10,000-agent swarm solving problems equals eight months ahead of Astra

Lisan al Gaib @scaling01Originally posted 2026.09.24

Open original on X

Based on my estimates, the 10,000-agent swarm that solved the Navier-Stokes problem was about 8 months of frontier progress ahead of a single GPT-6-Astra instance (with a range of 5.5 to 12.4 months) It used 48,000 times more output tokens than the largest single model evaluation and roughly 68 times more than an entire long-horizon coding benchmark

This post quotes another post: x.com/scaling01/status/2102788535191572709