Technology@lemmy.worldbybrianpeiris@lemmy.ca
15 hours

Announcing ARC-AGI-3 - A benchmark that tests if AI can explore, learn, and adapt in unfamiliar situations. Humans score 100%. Frontier AI scores 0.26%.

arcprize.org English

The ARC Prize organization designs benchmarks which are specifically crafted to demonstrate tasks that humans complete easily, but are difficult for AIs like LLMs, “Reasoning” models, and Agentic frameworks.

ARC-AGI-3 is the first fully interactive benchmark in the ARC-AGI series. ARC-AGI-3 represents hundreds of original turn-based environments, each handcrafted by a team of human game designers. There are no instructions, no rules, and no stated goals. To succeed, an AI agent must explore each environment on its own, figure out how it works, discover what winning looks like, and carry what it learns forward across increasingly difficult levels.

Previous ARC-AGI benchmarks predicted and tracked major AI breakthroughs, from reasoning models to coding agents. ARC-AGI-3 points to what’s next: the gap between AI that can follow instructions and AI that can genuinely explore, learn, and adapt in unfamiliar situations.

You can try the tasks yourself here: https://arcprize.org/arc-agi/3

Here is the current leaderboard for ARC-AGI 3, using state of the art models

  • OpenAI GPT-5.4 High - 0.3% success rate at $5.2K
  • Google Gemini 3.1 Pro - 0.2% success rate at $2.2K
  • Anthropic Opus 4.6 Max - 0.2% success rate at $8.9K
  • xAI Grok 4.20 Reasoning - 0.0% success rate $3.8K.

ARC-AGI 3 Leaderboard
(Logarithmic cost on the horizontal axis. Note that the vertical scale goes from 0% to 3% in this graph. If human scores were included, they would be at 100%, at the cost of approximately $250.)

https://arcprize.org/leaderboard

Technical report: https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf

In order for an environment to be included in ARC-AGI-3, it needs to pass the minimum “easy for humans” threshold. Each environment was attempted by 10 people. Only environments that could be fully solved by at least two human participants (independently) were considered for inclusion in the public, semi-private and fully-private sets. Many environments were solved by six or more people. As a reminder, an environment is considered solved only if the test taker was able to complete all levels, upon seeing the environment for the very first time. As such, all ARC-AGI-3 environments are verified to be 100% solvable by humans with no prior task-specific training

106
    Announcing ARC-AGI-3 | ARC Prize
    arcprize.org
    ARC-AGI-3 is the first fully-interactive benchmark in the ARC-AGI series, featuring hundreds of handcrafted games with thousands of levels.
    • sunbeam60@feddit.ukEnglish
      5 minutes

      Ii can thoroughly recommend “A Brief History of Intelligence” (by Max Bennett), which explains how intelligence has taken steps through evolution, what those steps were etc.

      Spatial intelligence requires spatial understanding and it’s not something that can be solved through a large language model, IMHO.

      I’m excited to see how these are solved. And I’m terrified to see how these will be solved.

    • Kissaki@feddit.orgEnglish
      30 minutes

      “Leaderboard” where rank one scores 0.3% success lol

      • brianpeiris@lemmy.caEnglish
        9 minutes

        You can really only judge fairness of the score if you understand the scoring criteria. It is a relative score where the baseline is 100% for humans – i.e. A task was only included in the challenge if at least two people in the panel of humans were able to solve it completely, and their action count is a measure of efficiency. This is the baseline used as a point of comparison.

        From the Technical Report:

        The procedure can be summarized as follows:
        • “Score the AI test taker by its per-level action efficiency” - For each level that the test taker completes, count the number of actions that it took.
        • “As compared to human baseline” - For each level that is counted, compare the AI agent’s action count to a human baseline, which we define as the second-best human action count. Ex: If the second-best human completed a level in only 10 actions, but the AI agent took 100 to complete it, then the AI agent scores (10/100)^2 for that level, which gets reported as 1%. Note that level scoring is calculated using the square of efficiency.
        • “Normalized per environment” - Each level is scored in isolation. Each individual level will get a score between 0% (very inefficient) 100% (matches or surpasses human level efficiency). The environment score will be a weighted-average of level score across all levels of that environment.
        • “Across all environments” - The total score will be the sum of individual environment scores divided by the total number of environments. This will be a score between 0% and 100%.

        So the humans “scored 100%” because that is the baseline by definition, and the AIs are evaluated at how close they got to human correctness and efficiency. So a score of 0.26% is 0.0026 times less efficient (and correct) compared to humans.

    • SuspciousCarrot78@lemmy.worldEnglish
      3 hours

      “…specifically crafted to demonstrate tasks that humans complete easily”

      Motherfucker, I can’t work out Minesweeper. I got zero fucking chance with your mystery box bloop game.

    • Sam_Bass@lemmy.worldEnglish
      4 hours

      AI code is prewritten and is unable to edit that. Humans edit their “code” every second

      • bss03@infosec.pubEnglish
        4 hours

        I couldn’t find replays. Are there more? Also, it is a bit funny that “building the bridge” which at one point seems to be Claude’s “chosen goal” is just “running out of moves” and failing the task.

        Task failed successfully, Claude. Task failed, successfully.

      • hamsterkill@lemmy.sdf.orgEnglish
        4 hours

        My understanding is that Claude is particularly geared towards being a tool for people to use rather than a human replacement. That’s why they had that whole spat with the Pentagon about a human needing to be in the loop.

    • UnrepentantAlgebra@lemmy.worldEnglish
      8 hours

      If human scores were included, they would be at 100%, at the cost of approximately $250

      Wait, why did it cost real humans $250 to pass the test?

      • KairuByte@lemmy.dbzer0.comEnglish
        6 hours

        I assume it’s an hourly wage or something. Just because humans can work for free if they choose, doesn’t mean they have no cost associated with them. Just like a company could choose to give away unlimited tokens, those tokens still have a standard cost.

      • brianpeiris@lemmy.caEnglish
        2 hours

        This is my rough upper-bound estimate based on the Technical Report. Human participants were paid to complete and evaluate the tasks at an average fixed fee of $128 plus $5 for solved tasks. So if a panel of humans were tasked with solving the 25 tasks in the public test set, it would be an average of $250 per person. Although, looking at it again, the costs listed for the LLMs is per task, so it would actually be more like $10 per human per task. In any case it’s one or two orders of magnitude less than the LLMs.

        Participants received a fixed participation fee of $115–$140 for completing the session, along with a $5 performance-based incentive for each environment successfully solved

        https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf

      • aesopjah@sh.itjust.worksEnglish
        5 hours

        it’s also an odd metric since only 20-60% of the humans completed it. Very 60% of the time they complete it everytime energy.

        Ideally they’d run the bots multiple times through (with no context or training of previous run), but I guess that is cost prohibitive?

        • monotremata@lemmy.caEnglish
          4 hours

          Yeah, this is what I was going to call out. Calling it “100% solvable by humans” and saying “if human scores were included, they would be at 100%” when 20-60% of humans solved each task seems kinda misleading. The AI scores are so low that I don’t think this kind of hyperbole is necessary; I assume there are some humans that scored 100%, but I would find it a lot more useful if they said something like “the worst-performing human in our sample was able to solve 45% of the tasks” or whatever. Given that the AIs are still scoring below 1%, that’s still pretty dark.

        • Aceticon@lemmy.dbzer0.comEnglish
          5 hours

          If there had been a “Buy 10, Get 1 free” they could’ve used 11 humans instead of 10 for the same $250.

    • Great Blue Heron@lemmy.caEnglish
      9 hours

      It’s fun to point at the crappy performance of current technology. But all I can think about is the amount of power and hardware the AI bros are going to burn through trying to improve their results.

      • partofthevoice@lemmy.zipEnglish
        5 hours

        Funnier yet will be if they continue to just train the model on that particular kind of test, invalidating its results in the process.

        • brianpeiris@lemmy.caEnglish
          2 hours

          It’s true that frontier models got better at the previous challenges, but it’s worth noting that they’re still not quite at human level even with those simpler tasks.

          Also, each generation of the challenge tries to close loopholes that newer models would exploit, like brute-forcing the training with tons of synthesized tasks and solutions, over-fitting to these particular kinds of tasks, and issues with the similarities between the tasks in the challenge.

          A common strategy in past challenges was to generate thousands of similar tasks, and you can imagine the big AI companies were able to do that at massive scale for their frontier models.

        • General_Effort@lemmy.worldEnglish
          5 hours

          Ok. I’m sure AGI-1 and AGI-2 weren’t real AGI. What number is the real AGI? Is it AGI-3?

          • brianpeiris@lemmy.caEnglish
            1 hour

            The goal of the ARC organization is to continually measure progress towards AGI, not come up with some predictive threshold for when AGI is achieved.

            As long as they can continue to measure a gap between “easy for humans” and “hard for AI”, they will continue releasing new iterations of this ARC-AGI challenge series. Currently they do that about once a year.

            More detail about the mission here: https://arcprize.org/arc-agi