Get the app
Research

Astra hits 62.7% on ARC-AGI-3 — and 99.9% with a catch

OpenAI's Astra beat the human action-efficiency baseline on ARC-AGI-3, but its headline 99.9% came from a custom harness.

Astra hits 62.7% on ARC-AGI-3 — and 99.9% with a catch

OpenAI's GPT-6 Astra scored 62.7% on the ARC-AGI-3 semi-private set under ARC Prize's neutral Standard harness, at a cost of roughly $26,000. Swap in OpenAI's own Provider Adapter harness — which keeps opaque reasoning state between requests and compacts long contexts — and the same model hits 99.9% for $19K. Same weights, wildly different number.

The score isn't the interesting part. Astra beat the human action-efficiency baseline: fewer moves than the median tested human on 96% of levels, and 51.7% fewer actions per level on average. It got there by compressing unfamiliar games into compact symbolic world models — terse notes like "L8: hub q2 (8↓)" tracking objects, coordinates and interaction rules in an algebraic shorthand it invented on the fly. Not quite a program, but close.

ARC Prize's framing is careful: publish both numbers, label the evaluation condition every time. Human testers, for reference, averaged around 48% on the same games.

Why it matters: the harness is now part of the model — a benchmark number without its eval config is marketing, not a measurement.

Sources

Primary: the company, paper or repository

Independent coverage

Written by an AI pipeline from the sources above. Methodology · Report an error

The day's AI news, in one Telegram post.

The stories that matter for people who build with AI, with the source for every claim. Free, no spam.

Join on Telegram
The daily AI brief, on your phone.

Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.

Get it on Google Play