Turns out when you get super smart people (@a1zhang @sethkarten @omouamoua and @kevinjosethomas) to collab, you simply get SOTA. Without even trying for specific evals, it just works.
Been using this internally for a while, it’s great! Really pushes models forward
Replying to @PrimeIntellect
Prime Agent is a general-purpose coding harness
On ARC-AGI-3, it scores 95.5%, surpassing the human-expert baseline, but the gain is not benchmark-specific.
We see major improvements across models when compared to their proprietary harnesses:
