GPT-6 Astra scores 62.7% on ARC-AGI-3, outacting humans on 96% of levels
Confirmed
Importance: historic (5 of 5)Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- Historic (5 of 5)
- Last verified
- 4 October 2026
Your AI and this story
- GPT-6 Astra126 days after its cutoff
- Claude Opus 5.565 days after its cutoff
- Gemini 4 Hydrogen156 days after its cutoff
- Grok 4.795 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 65 days before it.
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)
What happened
Six 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, so ARC Prize now reports both. ARC Prize said Astra “builds the most precise symbolic model of novel environments we’ve seen.”
Why it matters
ARC-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.
Sources
7 sources from 3 sites. Numbers match the chips in the text.
7 sources: 4 primary, 1 press, 2 reactions
Primary
- ARC Prize: OpenAI’s GPT-6 Astra on ARC-AGI-3arcprize.org, official
- ARC Prize results leaderboardarcprize.org, official
- ARC Prize on X: GPT-6.1 Sol on ARC-AGI (Verified)x.com, official
- ARC Prize on X: GPT-6 Sol on ARC-AGI (Verified)x.com, official
Press
- 36Kr: GPT-6 scores 99.9%, ARC exam forced remakeeu.36kr.com, press
Reactions
- ARC Prize on Xx.com, discussion
- François Chollet on X: Astra a ‘step-function change’ on ARC-AGI-3x.com, discussion
Changes
- Added GPT-6 Sol and GPT-6.1 Sol verified ARC-AGI-3 scores and Kaggle Milestone #2 results
- Added post link(s)
- Filed