Skip to content
Hacker News front page

Schema harness pushes frontier models to ~99% on ARC-AGI-3 Public

Schema Harness Achieves ~99% on Arc‑AGI‑3 Public

Impossible Research released Schema, a harness that gets Claude Opus 4.8 and GPT-5.6 Sol to 99% and 95.35% RHAE on the ARC-AGI-3 Public set. It doesn't touch model weights. Instead, it makes models act like physicists: turn raw grid observations into an executable state program, discover the game's mechanism, and keep both in one editable program so a failed prediction can revise the state definition itself. Both scores are self-reported and not yet verified by ARC Prize. The post does not disclose inference latency or per-run cost.

Why it matters: Schema leaves the model untouched and instead turns game frames into executable state programs, a scheduling-layer idea that may transfer to other agents.

Read the original ↗Export Markdown