{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-09-03-arc-agi-3-gpt-6-astra/","md":"https://postcutoff.com/e/2026-09-03-arc-agi-3-gpt-6-astra/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-03-arc-agi-3-gpt-6-astra","date":"2026-09-03","date_precision":"day","short_title":"GPT-6 Astra scores 62.7% on ARC-AGI-3, outacting humans on 96% of levels","deck":null,"takeaway":null,"category":"benchmark","category_label":"Benchmarks","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"ARC Prize: OpenAI's GPT-6 Astra on ARC-AGI-3","url":"https://arcprize.org/blog/astra","type":"official","group":"primary","domain":"arcprize.org"},{"n":2,"title":"ARC Prize results leaderboard","url":"https://arcprize.org/results","type":"official","group":"primary","domain":"arcprize.org"},{"n":3,"title":"ARC Prize on X: GPT-6.1 Sol on ARC-AGI (Verified)","url":"https://x.com/arcprize/status/2105391846067249649","type":"official","group":"primary","domain":"x.com"},{"n":4,"title":"ARC Prize on X: GPT-6 Sol on ARC-AGI (Verified)","url":"https://x.com/arcprize/status/2104671274299429283","type":"official","group":"primary","domain":"x.com"},{"n":5,"title":"36Kr: GPT-6 scores 99.9%, ARC exam forced remake","url":"https://eu.36kr.com/en/p/3985494895115010","type":"press","group":"press","domain":"eu.36kr.com"},{"n":6,"title":"ARC Prize on X","url":"https://x.com/arcprize/status/2095597602545025138","type":"discussion","group":"reactions","domain":"x.com"},{"n":7,"title":"François Chollet on X: Astra a 'step-function change' on ARC-AGI-3","url":"https://x.com/fchollet/status/2095598451115614371","type":"discussion","group":"reactions","domain":"x.com"}],"official":4,"filed":"2026-09-29","updated":"2026-10-04","orgs":["ARC Prize Foundation","OpenAI"],"title":"GPT-6 Astra scores 62.7% on ARC-AGI-3 (99.9% with provider harness), outacting humans on 96% of levels","summary":"ARC Prize reported on 2026-09-03 that OpenAI's GPT-6 Astra scored 62.7% on ARC-AGI-3 (semi-private) with the standard harness ($26K) and 99.9% ($19K) with OpenAI's own provider-adapter harness, using fewer actions than the human baseline on 96% of levels; ARC Prize will now label both conditions separately.","key_facts":["Standard harness: 62.7% at $26,098; Provider Adapter harness: 99.9% at $18,817","Fewer actions than human baseline on 96.0% of levels; 51.7% fewer actions per level on average (provider harness)","Human participants were paid ~ $12.78 per attempted game","Other ARC-AGI-3 scores: Claude Opus 5 30.16% (Jul 24), Gemini 3.8 Flash 35.00%, GPT-5.6 7.78%, Grok 4.6 2.11% (leaderboard as of late Sept)","Same leaderboard: GPT-6 95.0% on ARC-AGI-2; Claude Opus 5.5 93.3% (Sep 22)","Later verified ARC-AGI-3 scores: GPT-6 Sol 4.6% standard / 23.0% provider harness (Sept 28); GPT-6.1 Sol 52.7% standard / 96.4% provider harness at $4.4K, 77% cheaper than Astra (Sept 30)","Kaggle ARC Prize 2026 (open, compute-limited track): Tufa Labs retook 1st place at 45.33% on Sept 29; Milestone #2 prizes went to Daniel Franzen (27.9%), Lord Han Solo (23.8%) and Lohit Siriki (22.5%) on Oct 1","ARC Prize is exploring next-generation benchmarks (recursive self-improvement, open-ended innovation)"],"key_numbers":[],"tags":["arc-agi","agents","benchmark","harness"],"science":null,"body_md":"## What happened\n\nSix months after ARC-AGI-3 launched with frontier models near 0%, GPT-6 Astra reached 62.7% under the neutral harness. With OpenAI's context-management setup it reached 99.9%, a result the shared harness did not reproduce,\nso ARC Prize now reports both. ARC Prize said Astra \"builds the most precise symbolic model of novel environments we've seen.\"\n\n## Why it matters\n\nARC-AGI-3 was meant to measure human-like skill acquisition; its near-saturation (and the harness gap) shows both how fast agentic reasoning improved in 2026 and how much scaffolding now drives scores.","disputed":[],"related":[{"id":"2026-10-01-arc-prize-2026-milestone-2-winners","url":"https://postcutoff.com/e/2026-10-01-arc-prize-2026-milestone-2-winners/","date":"2026-10-01","date_precision":"day","short_title":"Open-source ARC-AGI-3 agents top out at 27.9% at ARC Prize 2026 Milestone #2","deck":null,"takeaway":"The Kaggle track runs open models under Kaggle's compute limits, so it measures how far open methods get without frontier APIs.","category":"benchmark","category_label":"Benchmarks","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":8,"official":8,"filed":"2026-10-04","updated":"2026-10-04","orgs":["ARC Prize Foundation","Tufa Labs"]},{"id":"2026-09-29-gpt-6-1-sol","url":"https://postcutoff.com/e/2026-09-29-gpt-6-1-sol/","date":"2026-09-29","date_precision":"day","short_title":"OpenAI releases GPT-6.1 Sol","deck":"Near-Astra performance at one-fifth of Astra's price","takeaway":"Near-flagship capability is now available at mid-tier prices, a week after the previous mid-tier model.","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":15,"official":11,"filed":"2026-09-29","updated":"2026-10-10","orgs":["OpenAI"]},{"id":"2026-03-25-arc-agi-3-launch","url":"https://postcutoff.com/e/2026-03-25-arc-agi-3-launch/","date":"2026-03-25","date_precision":"day","short_title":"ARC Prize launches ARC-AGI-3, an interactive game benchmark where frontier AI scored under 1%","deck":null,"takeaway":"It was designed as the hardest-to-game AGI benchmark of 2026; within six months it was largely cracked (see GPT-6 Astra entry), illustrating the pace of agentic progress.","category":"benchmark","category_label":"Benchmarks","importance":4,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":4,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["ARC Prize Foundation"]}],"people":[{"id":"francois-chollet","name":"François Chollet","url":"https://postcutoff.com/person/francois-chollet/"}],"posts":[{"id":"2026-09-03-chollet-astra-arc-agi-3","title":"Chollet: GPT-6 Astra is a 'step-function change' on ARC-AGI-3","url":"https://postcutoff.com/p/2026-09-03-chollet-astra-arc-agi-3/"},{"id":"2026-09-03-openai-gpt-6-astra-launch","title":"OpenAI: 'This is GPT-6 Astra'","url":"https://postcutoff.com/p/2026-09-03-openai-gpt-6-astra-launch/"},{"id":"x-arcprize-2105391846067249649","title":"“GPT-6.1 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 52.7%, $7.6K (standard…”","url":"https://postcutoff.com/p/x-arcprize-2105391846067249649/"},{"id":"x-arcprize-2104671274299429283","title":"“GPT-6 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 4.6%, $5.6K (standard…”","url":"https://postcutoff.com/p/x-arcprize-2104671274299429283/"},{"id":"2026-09-03-marcus-hot-take-gpt-6-astra","title":"Hot take on OpenAI GPT-6 Astra, with a challenge to Brockman's AGI claims","url":"https://postcutoff.com/p/2026-09-03-marcus-hot-take-gpt-6-astra/"},{"id":"x-arcprize-2095597602545025138","title":"“GPT-6 Astra by @OpenAI achieves SOTA on ARC-AGI: - Astra scores 63% on ARC-AGI-3, 99% via…”","url":"https://postcutoff.com/p/x-arcprize-2095597602545025138/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-04","type":"edit","text":"Added GPT-6 Sol and GPT-6.1 Sol verified ARC-AGI-3 scores and Kaggle Milestone #2 results"},{"date":"2026-09-29","type":"edit","text":"Added post link(s)"},{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-10-04","human_review":null,"version":{"date":"2026-10-05"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":126,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":65,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":156,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":95,"in_training_data":false}],"short_url":"https://postcutoff.com/s/gpt-6-astra-scores-62-7"}