Evals Benchmarks Harness Engineering GPT-6 Astra

ARC-AGI-3

A benchmark for measuring intelligence in interactive environments

An ARC Prize Foundation benchmark and competition environment for evaluating AI agents on novel interactive visual tasks.

Recent stories

1 linked story

newsSECONDARY2026-09-03

ARC Prize reports GPT-6 Astra scores 62.7% or 99.9% on ARC-AGI-3 by harness

ARC Prize reports GPT-6 Astra scored 62.7% on ARC-AGI-3 with its provider-neutral harness, versus 99.9% with OpenAI's provider adapter. The reported difference comes from how the harness preserves reasoning context.