Prime Agent Coding Harness Tops ARC-AGI-3 with 95.5% Beating Human Experts

xeophon · x · 2026-08-06

PrimeIntellect has released Prime Agent, a general-purpose coding agent harness. It achieves a score of 95.5% on the ARC-AGI-3 benchmark, officially surpassing the human-expert baseline.

According to developers, the harness wasn't specifically optimized for this benchmark. However, when compared against their proprietary harnesses, models show major across-the-board improvements, simply working out of the box to push model capabilities forward.

Related event: PrimeIntellect Launches Prime Agent, Topping ARC-AGI-3(5 posts)→

Original post →

More from coding & agent

coding & agent channel →