The Arc Prize Basis, a nonprofit co-founded by outstanding AI researcher François Chollet, introduced in a weblog put up on Monday that it has created a brand new, difficult take a look at to measure the overall intelligence of main AI fashions.
To date, the brand new take a look at, known as ARC-AGI-2, has stumped most fashions.
“Reasoning” AI fashions like OpenAI’s o1-pro and DeepSeek’s R1 rating between 1% and 1.3% on ARC-AGI-2, in accordance with the Arc Prize leaderboard. Highly effective non-reasoning fashions together with GPT-4.5, Claude 3.7 Sonnet, and Gemini 2.0 Flash rating round 1%.
The ARC-AGI assessments encompass puzzle-like issues the place an AI has to determine visible patterns from a set of different-colored squares, and generate the right “reply” grid. The issues have been designed to pressure an AI to adapt to new issues it hasn’t seen earlier than.
The Arc Prize Basis had over 400 folks take ARC-AGI-2 to ascertain a human baseline. On common, “panels” of those folks received 60% of the take a look at’s questions proper — significantly better than any of the fashions’ scores.
In a put up on X, Chollet claimed ARC-AGI-2 is a greater measure of an AI mannequin’s precise intelligence than the primary iteration of the take a look at, ARC-AGI-1. The Arc Prize Basis’s assessments are geared toward evaluating whether or not an AI system can effectively purchase new abilities exterior the information it was educated on.
Chollet mentioned that not like ARC-AGI-1, the brand new take a look at prevents AI fashions from counting on “brute pressure” — in depth computing energy — to search out options. Chollet beforehand acknowledged this was a serious flaw of ARC-AGI-1.
To handle the primary take a look at’s flaws, ARC-AGI-2 introduces a brand new metric: effectivity. It additionally requires fashions to interpret patterns on the fly as a substitute of counting on memorization.
“Intelligence just isn’t solely outlined by the power to unravel issues or obtain excessive scores,” Arc Prize Basis co-founder Greg Kamradt wrote in a weblog put up. “The effectivity with which these capabilities are acquired and deployed is an important, defining part. The core query being requested is not only, ‘Can AI purchase [the] talent to unravel a job?’ but additionally, ‘At what effectivity or price?’”
ARC-AGI-1 was unbeaten for roughly 5 years till December 2024, when OpenAI launched its superior reasoning mannequin, o3, which outperformed all different AI fashions and matched human efficiency on the analysis. Nevertheless, as we famous on the time, o3’s efficiency beneficial properties on ARC-AGI-1 got here with a hefty price ticket.
The model of OpenAI’s o3 mannequin — o3 (low) — that was first to achieve new heights on ARC-AGI-1, scoring 75.7% on the take a look at, received a measly 4% on ARC-AGI-2 utilizing $200 value of computing energy per job.
The arrival of ARC-AGI-2 comes as many within the tech trade are calling for brand spanking new, unsaturated benchmarks to measure AI progress. Hugging Face’s co-founder, Thomas Wolf, lately informed TechCrunch that the AI trade lacks enough assessments to measure the important thing traits of so-called synthetic basic intelligence, together with creativity.
Alongside the brand new benchmark, the Arc Prize Basis introduced a brand new Arc Prize 2025 contest, difficult builders to achieve 85% accuracy on the ARC-AGI-2 take a look at whereas solely spending $0.42 per job.
