24 comments

  • kelvinjps10 a few seconds ago

    Chat got ones were slow on Firefox mobile

  • dadoum an hour ago

    I tried to one-shot the first test (the Rubik's Cube test) with LucidQuery's Swift model, to test it, as there are not much benchmarks about it and that they brag a lot about it, and I was pleasantly surprised to see it achieving a result similar to Grok 4.5 but in one shot (there is the same issue that if you scramble twice the solve button does not work anymore, but it got it in one shot).

    Though it crunched most of the free quota, 47111 tokens, so I couldn't make multiple attempts.

  • HeavyStorm 29 minutes ago

    Excellent idea, most terrible execution. Comparison are completely subjective, problem space is too simplistic for today's AI, the resultstable simply ignores that a face isn't a cube (therefore, gpt 5 shouldn't have 100% success) and the retry is uneven. Also, given the random nature of AI, sampling once each model isn't very scientific.

    This feels like a kid trying to do science. The will is there, but lacks experience.

  • jeffgreco an hour ago

    So strange to write a whole post with Claude giving the best results and Grok consistently the worst, but awarding Grok the winner because at least it did the worst fastest?

    • singingtoday an hour ago

      GPT was the worst on the Rubik's cube

      • GaggiX 40 minutes ago

        Grok did not render anything, they had to prompt it again.

  • mlmonkey an hour ago

    I am 99% sure the post was written by AI

    • jszymborski an hour ago

      The honest takeaway: this is 100% written by an LLM.

      • mlmonkey 39 minutes ago

        That was the honest giveaway ... :-D

    • dwa3592 an hour ago

      i will give you the remaining 1% because i felt the same way.

  • singingtoday an hour ago

    Love the idea, I think more complex games would show the gap in ability better.

    Do it again but this time get them to make a multiplayer online Jetmen REVIVAL game. Online play is key, because it's very complex. Jetmen is a good game for this since it has physics and customization that's complex enough but still simple.

  • Zebfross 20 minutes ago

    Isn’t the number of turns most important? Some agents take repeated input, while others can mostly one-shot what I’m looking for.

  • paxys an hour ago

    Why not wait one more day for GPT-5.6?

    • acters an hour ago

      I worry that GPT 5.6 will be heavily restricted and have the same feature to fallback to another model like Claude fable 5 does all too often. That fallback shenanigans mess up actual benchmarks and I don't like it.

    • m4rkuskk an hour ago

      That will be in the Part 2 article.

    • faitswulff an hour ago

      Also throw in GLM 5.2 for good measure

    • foxfired an hour ago

      If we wait for the next models, we will never test anything because there will always be another model. Like the Ai Scotsman:

      > "Nay, laddie, that’s no’ the real AI Scotsman! He’s grander still! More powerful! Just wait for the next model!"

    • fluidcruft an hour ago

      And why not Sonnet?

  • thorum 33 minutes ago

    Interesting that all four models converge on such similar designs, for such short prompts.

    • HeavyStorm 27 minutes ago

      They were trained pretty much on the same data.

  • maxdo an hour ago

    Tried at work , this release def a moment I will remember. My work is not the same . The model is the first model that offer exactly as I want :

    For hard tasks , that needs precision I will wait and pay expensive tokens

    For everything else , query data , logs, rolling out releases , I’m using grok and it’s much better vs other tools and much cheaper too .

  • Kuyawa 34 minutes ago

    I'd like to see the comparisons with DeepSeek, Qwen, Mimo, Kimi and GLM

  • RickS an hour ago

    Barring the retry thing, n=1 on all models? Am I misreading, or is this a joke?

    Variance in quality on these things is so, so high.

  • krauq 42 minutes ago

    Too nice to Grok, if there are really cost savings it should say how much each of the three demos cost so we can judge if it's worth the lower quality (probably not). The time to complete each would also be interesting.