Google,Switzerland erotic OpenAI, DeepSeek, et al. are nowhere near achieving AGI (Artificial General Intelligence), according to a new benchmark.
The Arc Prize Foundation, a nonprofit that measures AGI progress, has a new benchmark that is stumping the leading AI models. The test, called ARC-AGI-2 is the second edition ARC-AGI benchmark that tests models on general intelligence by challenging them to solve visual puzzles using pattern recognition, context clues, and reasoning.
This Tweet is currently unavailable. It might be loading or has been removed.
According to the ARC-AGI leaderboard, OpenAI's most advanced model o3-low scored 4 percent. Google's Gemini 2.0 Flash and DeepSeek R1 both scored 1.3 percent. Anthropic's most advanced model, Claude 3.7 with an 8K token limit (which refers to the amount of tokens used to process an answer) scored 0.9 percent.
The question of how and when AGI will be achieved remains as heated as ever, with various factions bickering about the timeline or whether it's even possible. Anthropic CEO Dario Amodei said it could take as little as two to three years, and OpenAI CEO Sam Altman said "it's achievable with current hardware." But experts like Gary Marcus and Yann LeCun say the technology isn't there yet and it doesn't take an expert to see how fueling AGI hype is advantageous to AI companies seeking major investments.
The ARC-AGI benchmark is designed to challenge AI models beyond specialized intelligence by avoiding the memorization trap — spewing out PhD-level responses without an understanding of what it means. Instead it focuses on puzzles that are relatively easy for humans to solve because of our innate ability to take in new information and make inferences, thus revealing gaps that can't be resolved by simply feeding AI models more data.
"Intelligence requires the ability to generalize from limited experience and apply knowledge in new, unexpected situations. AI systems are already superhuman in many specific domains (e.g., playing Go and image recognition)" read the announcement.
SEE ALSO: I compared Sesame to ChatGPT voice mode and I'm unnerved"However, these are narrow, specialized capabilities. The 'human-ai gap' reveals what's missing for general intelligence - highly efficiently acquiring new skills."
To get a sense of AI models' current limitations, you can take the ARC-AGI test for yourself. And you might be surprised by its simplicity. There's some critical thinking involved, but the ARC-AGI test wouldn't be out of place next to the New York Timescrossword puzzle, Wordle, or any of the other popular brain teasers. It's challenging but not impossible and the answer is there in the puzzle's logic, which is something the human brain has evolved to interpret.
OpenAI's o3-low model scored 75.7 percent on the first edition of ARC-AGI. By comparison, its 4 percent score on the second edition shows how difficult the test is, but also how there's a lot more work to be done with reaching human level intelligence.
Topics Google OpenAI
Good riddance: The web's top deepfake porn site is shutting downFree Krispy Kreme: How to get free original glazed doughnutJBL Tune 510BT Headphones deal: Take 25% offApple launches Shazam Viral Charts to track those overnight blowout hitsBest kids deal: Save 22% on the Kindle Paperwhite KidsGood riddance: The web's top deepfake porn site is shutting downOura Ring launches glucose monitoring in partnership with DexcomToday's Hurdle hints and answers for May 7, 2025JBL Tune 510BT Headphones deal: Take 25% offNYT Strands hints, answers for May 7Best Apple M4 MacBook Air deal: Save $150 on new MacBook AirGoogle launches 100 Zeroes TV and movie production initiativeBest tracker deal: Get a 4Government messages on modded Signal clone Telemessage got hackedJBL Tune 510BT Headphones deal: Take 25% offBest Amazon deal: Use code ECHOSPOT25 to save $25Best smartwatch deal: Save $50 on Fitbit Versa 4MrBeast is teaming with 'Maximum Ride' author James Patterson to write a novelInter Milan vs. Barcelona 2025 livestream: Watch Champions League for freeNYT mini crossword answers for May 8, 2025 Xpeng's flying car unit hires banks for IPO: report · TechNode Japan’s Nissan receives more than 20,000 non VALORANT Mobile test server by Tencent to launch on June 12, pre Chinese GPU maker MetaX completes IPO counseling · TechNode NVIDIA reportedly plans to establish research center in Shanghai · TechNode DJI launches Mavic 4 Pro with 360° camera rotation and 100MP Hasselblad sensor · TechNode CATL says it is first to meet China’s new battery safety standards · TechNode Tencent eyeing $15 billion acquisition of game developer Nexon: report · TechNode Qualcomm bets on on China’s Xpeng to sell redesigned P7 sports sedan in Q3 · TechNode Xiaomi CEO expects EV business to break even later this year · TechNode Exec from Chinese automaker GAC met Brazilian president, planning EV factory · TechNode Honor reveals design of Honor 400 series smartphones ahead of global launch · TechNode Nintendo Switch 2 launches in China with over 400,000 pre Shanghai cracks down on illegal AI content on major platforms · TechNode China’s Xpeng aims to double sales and break even this year: CEO · TechNode Xiaomi Redmi Turbo 4 Pro reaches one million units sold in under a month · TechNode Multiple Chinese cities pause trade Tencent not in talks to acquire Nexon, source says: report · TechNode Great Wall Motor’s CEO goes public criticizing BYD over unfair competition · TechNode
2.5682s , 8224.828125 kb
Copyright © 2025 Powered by 【Switzerland erotic】,Exquisite Information Network