Simular's Neurosymbolic Agent Tops OSWorld 2.0 Benchmark

xwang_lk · x · 2026-08-28

Simular AI's computer-use agent, Sai Borg, has beaten Opus 5 and GPT-5.6 Sol on the OSWorld 2.0 benchmark, achieving a score of 73% on complex tasks. The success is attributed to a neurosymbolic framework that pairs neural network exploration with symbolic code logic, delivering high reliability at about two-thirds the cost of competitors.

Related event: Simular's Sai Agent Tops OSWorld 2.0 at Two-Thirds the Cost(4 posts)→

Original post →

More from coding & agent

coding & agent channel →