LLM Ass Bench

(assbench.com)

142 points | by fragmede 8 hours ago ago

37 comments

  • drywater2 7 hours ago

    Finally, I was getting tired of seeing pelicans on a bike.

    • schainks 6 hours ago

      Up next, Pelican ass-bench!

  • athrowaway3z 6 hours ago

    6 months from now we'll be discussing if model training is assmaxxing.

  • ravenstine 6 hours ago

    I'm impressed that Luna got as far as it did on max reasoning. Don't get me wrong, that's one weird looking ass, but even the top GPT model a year ago probably would have done worse based on my experience (with asking it to create meshes in general, not modeling asses... yeah, that's the ticket). Then again, I'm also not, because I've found it to be a great deal at its relatively low price point when the reasoning is set to high.

  • variety8675 8 hours ago

    The idea that they're going to benchmaxx this in the future amuses me

  • sethkim 6 hours ago

    Folks, we've reached the top.

    • bogzz 6 hours ago

      It's about bottoms though...?

  • spottedmarley 7 hours ago

    ASStra for the win!

  • ramon156 7 hours ago

    how come opus 5.5 did so well? I'm surprised

    • pixl97 6 hours ago

      Na, not well at all. Now Fable, fable like'em thick.

    • snowram 6 hours ago

      Because it is ass.

    • ggerules 6 hours ago

      Better data set?

  • TutleCpt 6 hours ago

    The prompt that created these images doesn't mention that they want a Caucasian skin color. Huh. Racist LLMs?

    • comradesmith 6 hours ago

      It’s only a sample of one per model

    • ggerules 6 hours ago

      Biased data?

    • throwaway743 6 hours ago

      Makes sense. Most look like pancake butts or shitty implants.

  • devinprater 5 hours ago

    Next, HumanBench! Draw an entire, picture-perfect human.

  • Ancalagon 7 hours ago

    nsfw?

    but hilarious nonetheless

    • sanex 7 hours ago

      It's ok they're wearing thongs it's not nudity.

      • Ancalagon 7 hours ago

        still awkward when a page full of thong-covered asses pops up on my extra monitor in my open-seating arrangement office that im required to attend 4 times a week (no of course im not salty or anything)

        • tripleee 6 hours ago

          its only awkward if you quickly close it as if embarrassed

          leave it up all day so others know it's intentional

          • pyrale 6 hours ago

            Make an all-team demo on new frontiers in benchmarking technology.

          • knicholes 6 hours ago

            Assert your dominance

            • tripleee 6 hours ago

              jiggle one of the butts while making eye contact with passers-by

        • mosselman 7 hours ago

          You shouldn't ASSume a link with a name like this is sfw.

        • jahnu 6 hours ago

          Have you tried a few toots on an air horn to indicate to your colleagues that the thing on the screen was unexpected?

    • dbt00 6 hours ago

      Agree 2x.

  • danbrooks 6 hours ago

    Glad my work blocked this. But can we get a NSFW tag? If this is NSFW?

    • comradesmith 6 hours ago

      It’s fine. You’ll be fine

    • zulux 3 hours ago

      I go to church every week. I try not to swear.

      The site is fine, and it's funny to my inner 13-year-old boy.

    • fg137 6 hours ago

      If I were you I wouldn't rush to open a website that clearly has "ass" in the title

  • fragmede 8 hours ago

    The most important of benchmarks.

  • winddude 7 hours ago

    haha, doing the important work!

  • visiondude 6 hours ago

    i almost wrote a extension to block mentions of pelican bench because i find those so utterly useless. now, Assbench, on the other hand, i could get behind

  • sergiotapia 6 hours ago

    But can we make thicc pelicans?

  • Rapzid 6 hours ago

    We need Banana Bench next.

  • randomblock1 6 hours ago

    Now put them on a bike.