Accelerating GPT-5.6 Sol Ultrafast

116 points | by pr337h4m an hour ago

23 comments

  • iamcoder18 24 minutes ago

    I've been waiting so long for something amazing to come out of the OpenAI and Cerebras collaboration.

    > In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a single working day, achieving comparable accuracy nearly 7× faster.

    This is actually insane.

    Hopefully the release ultrafast of Terra and Luna too.

      piyh 19 minutes ago

      Feels like the 90's again where single threaded speed is improving fast. ASICs and wafer scale rather than node shrinks, but end result to me the consumer feels the same.

  • owentbrown 3 minutes ago

    Whoa. This looks both powerful and expensive.

    My prediction is that, this time next year, top developers outside ai labs will be spending 50k USD+ on inference.

    Within labs, I've heard spend is already far beyond this per developer.

  • wxw 42 minutes ago

    > Compared with output speeds reported by Artificial Analysis GPT-5.6 Sol on Ultrafast mode runs 11x faster than Fable 5, and 5x faster than Opus 4.8 on Fast mode.

    Awesome work. I'm personally very excited for faster models/inference.

    I think speed is underrated to some degree in the current conversation. For a while, I was using Cursor's Composer quite a lot, even over frontier models, just because of how darn fast it was.

      kilroy123 36 minutes ago

      I've been using DeepSeek flash a lot this week to try it out. Now, I deeply want the smart frontier models to be just as fast.

  • GodelNumbering 42 minutes ago

    The corresponding OpenAI post https://openai.com/index/previewing-ultrafast/

    There is no pricing info, which could mean it's "if you have to ask..." territory or they are simply gauging interest before deciding

      rirze 35 minutes ago

      They're expanding access to companies that apply for the program and explain their use cases. So it's very real but limited imo.

        WarmWash 17 minutes ago

        The stake in the side of cerebras has always been that the economics are pretty poor.

        Who knows if they will subsidizes it to mitigate sticker shock, but it's a safe assumption that it will be scarily expensive. However if you are in a "cost is no obstacle, speed is god" position, it will likely be pure magic.

          fcarraldo 11 minutes ago

          Can anyone explain why Cerberus needs to be _fast_ instead of _cheap_?

          I don't think I understand why they aren't leveraging the increased speed to do batching to serve more customers at a "normal" tok/s.

          Is the limitation, even on cerberus, still that the cache can only serve so many concurrent sessions over time? Is there no scaling advantage? I genuinely do not understand how any of this works.

  • ricardobeat 8 minutes ago

    The omission of Mimo v2.5-Pro Ultraspeed, released in June, which can achieve 1000tok/s is an interesting flaw in the comparison graphs.

    It is a bit outdated (scores ± 40% lower), but smart enough for a lot of coding tasks, and can cost under 1/10th of Sol.

    https://mimo.mi.com/models/en-US/mimo-v2.5-pro-ultraspeed

  • anthonypasq 4 minutes ago

    I'd just like to point out that the largest model Cerebras has ever served is Kimi K2.6 which is 1T parameters, so that either means that theyve had a breakthrough on the hardware engineering side of things, or GPT-5.6 Sol is likely a lot smaller than people think.

    If it truly is only ~1-2T parameters, then this kinda kills 2 narratives for me.

    1. all the handwringing about open source catching up via Kimi K3 (3T params) is complete nonsense. All that matters imo for determining which labs are leading is intelligence per parameter. Anyone with a enough compute can train a giant model, but being able to squeeze capabilities into smaller models gives you a massive inference and training edge.

    2. Inference margins are clearly insane, and this explains why OpenAI was able to lower the price of Luna by 80%. Id guess that thing is probably 120b params based on the TPS they are serving it at.

  • fg137 9 minutes ago

    > allowing Sol Ultrafast to accelerate your most time-sensitive, mission-critical work

    Curious, what are some of the use cases?

  • storus 22 minutes ago

    Wow, that's even faster than diffusion LLMs but with the Fable-level quality! Congrats!

  • thraway3837 36 minutes ago

    This is really cool. Someone here commented about similarity between this and hardware advancements for AV encode/decode.

    I think it's only a matter of time before miniaturization can have a thumbnail sized user-replaceable accessory that contains the LLM built onto the hardware. I admit I don't know how any of that works, but would be amazing to experience. Fully local, fully offline, ultra fast local inference better than any personal computing product.

  • crazysim 42 minutes ago

    GPT 5.6 Luna Ultrafast when?

  • HawtAds an hour ago

    Their dinner plate chips are impressive.

  • behnamoh 11 minutes ago

    Fast mode is already 1.5 times faster and 2x more expensive in the Codex subscription plan. If this thing is 14 times faster, then I can imagine running out of my quota in one session.

  • scotty79 22 minutes ago

    I swear that now frontier AI stuff comes out few times a week.

  • poly2it 40 minutes ago

    I guess Gemini 3.7 Flash is no longer at the pareto frontier of speed to intelligence.

      odo1242 31 minutes ago

      Well, there’s still price

  • applfanboysbgon 12 minutes ago

    This kills the crab.

    Compilation time will be a genuine bottleneck for slop coding if this becomes the standard generation rate over the next few years. Go, Zig or even C99 with TCC for dev builds, any language that can get you systems-level performance (or close to it) in a dev environment where you can iterate in ms rather than minutes is going to be immensely more appealing than generating a potential prototype in 10 seconds and waiting 15 minutes for it to compile.

      yetihehe 6 minutes ago

      Maybe then LLM's will switch to outputting raw machine code?