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.
More from coding & agent
- DeepMind turns coding agent Antigravity into a science tool, surfacing novel antimicrobial peptide in one session — pushmeet · 2026-10-16
- Cross-review coding workflow: Claude writes the plan, Codex audits it — theteknosaur · 2026-10-16
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Normalizing Claude's schema-free MCP output before it hits downstream n8n nodes — snowingbol · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- A plain notes.md fixed my agent's cross-session amnesia better than chat history — rahul_watertech · 2026-10-16