Prime Intellect Releases Prime Agent, Topping ARC-AGI-3 Human Baseline

omarabudayyeh · x · 2026-08-06

Prime Intellect has launched Prime Agent, a self-improving harness designed for coding and long-running autonomous tasks.

The team reports that the system achieved 95.5% on the ARC-AGI-3 benchmark, surpassing the human baseline, and claims that this performance gain is not specific to benchmark overfitting.

Related event: PrimeIntellect open-sources Prime Agent, scores 95.5% on ARC-AGI-3, beating human experts(40 posts)→

Original post →

More from coding & agent

coding & agent channel →