Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-02-24 · source-backed
Chollet confirmed GPT-5.2 at 46-50%, Poetiq at 54%. But he cautions: "Saturating ARC does not mean we have AGI." ARC-AGI-3 launches March 25 with harder abstractions. For builders, the current benchmark race validates that agent scaffolding improvements (not just model improvements) drive capability gains.
Each link below shares sources, entities, or timing with this story.
GPT-5.4 scores 0.26%. Opus 4.6 scores 0.25%. Grok-4.20 scores 0.00%. Humans score 100%. The Decoder covered the ARC-AGI-3 launch on March 25, and the results make every "AGI is here" claim look premature. François Chollet launched ARC-AGI-3 at Y Combinator HQ alongside a fires...
First interactive reasoning benchmark. Top agent (StochasticGoose) scored 12.58% vs. humans. "Intelligence is efficiency." Agents struggle to convert environmental feedback into coherent strategies. Full launch March 25. ARC Prize
The ARC Prize Foundation is launching ARC-AGI-3, the first major format change since 2019. Unlike versions 1 and 2 (static visual reasoning), version 3 uses game-like environments where agents explore without instructions, discover rules, and adapt to hand-crafted levels that...
Drops static puzzles for interactive games where agents must figure out rules through exploration. First format change since 2019. Preview: most humans beat the games easily; AI agents struggle. ARC Prize
The biggest single-benchmark jump in a frontier model update: 37.6% → 68.8% on ARC-AGI-2. For comparison, GPT-5.2 scored 54.2%, Gemini 3 Pro 45.1%. ARC-AGI-2 measures novel problem-solving on adversarially constructed tasks. A near-doubling suggests genuine reasoning improveme...
The ARC Prize Foundation dropped ARC-AGI-3 on March 25 and the results broke my mental model of how AI capability scales. Symbolica's Arcgentica framework scored 36.08% (113 of 182 playable levels, 7 of 25 games completed) using Claude Opus 4.6 as its backbone. Cost: $1,005. F...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.