GPT-6 Astra represents a step-function change in model capability for interactive reasoning problems. It scores 66% on ARC-AGI-3 using our standard harness, and nearly 100% with a continuous conversation harness and custom compaction, at a cost of roughly $360 per game.In fact,…— François Chollet (@fchollet) September 3, 2026
ARC-AGI-3
ARC-AGI-3 is the first interactive reasoning benchmark for AI agents—play as humans and build agents that learn in novel environments.
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.
Alex MacCaw on Twitter / X
I suspect generalized reasoning was solved just a few weeks ago and it flew completely under the radar.HRM, a new arch, reportedly has SOTA results on ARC-AGI 1 & 2 benchmarks with only 27 million parameters and ~1k training examples.— Alex MacCaw (@maccaw) July 25, 2025
François Chollet on Twitter / X
Quick reminder of what's ok vs not ok with harnesses used for playing ARC-AGI-3:1. Not okay: harnesses that were custom-made to solve the benchmark or that contain knowledge about the benchmark format / contents.2. Fine: general-purpose API settings that were not developed…— François Chollet (@fchollet) July 30, 2026
GPT-6 Astra: The System Card, Alignment and What Comes Next
OpenAI claims that Astra is ‘the most intelligent and most aligned [available] model’ in the world.
GPT-6 Astra: A new generation of intelligence
Introducing GPT-6 Astra, our most intelligent and aligned model yet, with state-of-the-art capabilities across computer use, coding, cybersecurity, and science.
OpenAI's GPT-6.1 Sol offers Astra-like performance at 1/5th price. A new Ultrafast tier clocks at 300 tokens per second.
Its obvious targets are applications where waiting carries its own cost: interactive coding, customer support, financial analysis, incident response and other human-in-the-loop systems.
gpt-oss:120b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
ARC Prize on Twitter / X
OpenAI’s internal testing shows that provider-managed conversation state preserves greater continuity across turns and improves performance on long-horizon tasks like ARC-AGI-3. This is a real and useful result. We’re encouraged to see ARC used to identify useful harness design.… https://t.co/6Xk2Op0Sls— ARC Prize (@arcprize) July 30, 2026
gpt-oss:20b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action sequences without explicit instructions. Like its predecessors ARC-AGI-1 and 2, ARC-AGI-3 focuses entirely on evaluating fluid adaptive efficiency on novel tasks, while avoiding language and external knowledge. ARC-AGI-3 environments only leverage Core Knowledge priors and are difficulty-calibrated via extensive testing with human test-takers. Our testing shows humans can solve 100% of the environments, in contrast to frontier AI systems which, as of March 2026, score below 1%. In this paper, we present the benchmark design, its efficiency-based scoring framework grounded in human action baselines, and the methodology used to construct, validate, and calibrate the environments.
OpenAI's Unreleased Model Astra Solves Ten Major Open Mathematics Problems
Math is hard.
Diogo Almeida on Twitter / X
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev• 20-200x faster• 40-400x… pic.twitter.com/JSybNG2BKJ— Diogo Almeida (@CompleteSkeptic) September 15, 2026
Making a Game Boy Advance game with GPT-6 Astra - Sprite Fusion
I made a Game Boy Advance game using GPT-6 Astra and an AI pixel art generator. See the prompts and play the demo.
