OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

(developers.openai.com)

116 points | by arabicalories 1 hour ago

16 comments

  • guilamu 17 minutes ago
    Just tested it on my homemade Wordpress+GravityForms benchmark and it's one of the worst model of the leaderboard performance wise and the worst value wise: https://github.com/guilamu/llms-wordpress-plugin-benchmark

    I know it's only on a single benchmark, but I dont understand how it can be so bad...

    • mosselman 4 minutes ago
      You even traveled in time to deliver us this benchmark.

      I really like this benchmarking. Have you evaluated the judge benchmark somehow? I'd love to setup my own similar benchmark.

    • ac29 7 minutes ago
      Your benchmark has Opus 4.7 performing significantly worse than Sonnet 4.6. Even if true on your benchmark, that is not representative of the overall performance of the models.
  • wincy 38 minutes ago
    Just tried it out for a prod issue was experiencing. Claude never does this sort of thing, I had it write an update statement after doing some troubleshooting, and I said “okay let’s write this in a transaction with a rollback” and GPT-5.5 gave me the old “okay,

    BEGIN TRAN;

    -- put the query here

    commit;

    I feel like I haven’t had to prod a model to actually do what I told it to in awhile so that was a shock. I guess that it does use fewer tokens that way, just annoying when I’m paying for the “cutting edge” model to have it be lazy on me like that.

    This is in Cursor the model popped up and so I tried it out from the model selector.

    • XCSme 25 minutes ago
      I feel like the last 2-3 generations of models (after gpt-5.3-codex) didn't really improve much, just changed stuff around and making different tradeoffs.
      • pixel_popping 22 minutes ago
        I disagree, it improved enormously especially at staying consistent for long-tasks, I have a task running for 32 days (400M+ tokens) via Codex and that's only since gpt-5.4
        • lowdude 0 minutes ago
          That’s actually crazy, what kind of task is that? And is that a recurring kind of task like some analysis, or coding related?
        • ericpauley 19 minutes ago
          Has that task accomplished anything yet?
          • codemog 11 minutes ago
            I think the OP is in for a rude surprise when the task is “finished”.
          • xp84 15 minutes ago
            Too soon to tell, give it a billion tokens before we make up our minds
            • pixel_popping 2 minutes ago
              Oh boy, you are far from what it requires, we are probably talking 3B+, but note that this is just codex, obviously codex is also doing automatic adversarial with the regular zoo (gemini-3.1-pro-preview, opus-4.6/4.7, gpt-5.3-codex, minimax-2.7, glm-5.1, mimo-2 (now 2.5) and so-on, you get the gist) :)
          • SecretDreams 6 minutes ago
            Kept the OP employed for a full extra month at their hire AI metric firm, hopefully.
    • syspec 26 minutes ago
      Can't tell if above is good or bad.
  • ftonon 15 minutes ago
    Looks like the default config in the chat is instant 5.3, it only uses the 5.5 on the thinking variant
  • neosat 1 hour ago
    Enterprise user here and still seeing only 5.4. Yesterday's announcement said that it will take a few hours to roll out to everybody. OpenAI needs better GTM to set the right expectations.
    • neosat 39 minutes ago
      Just refreshed and see 5.5 now - yay! Love the speedy resolution ;) Thanks folks, I'll complain faster next time....
  • czk 1 hour ago
    API page lists the knowledge cutoff as Dec 01, 2025 but when prompting the model it says June 2024.

       Knowledge cutoff: 2024-06
       Current date: 2026-04-24
    
       You are an AI assistant accessed via an API.
    • BeetleB 41 minutes ago
      I don't know why this keeps coming up. This has always been the least reliable way to know the cutoff date (and indeed, it may well have been trained on sites with comments like these!)

      Just ask it about an event that happened shortly before Dec 1, 2025. Sporting event, preferably.

      • czk 37 minutes ago
        the model obviously knows things after the reported date but its just curious that it reports that date consistently

        could be they do it intentionally to encourage more tool calls/searches or for tuning reasons

    • htrp 1 hour ago
      Can you really believe things that the model says? (A lot of prior model api pages say knowledge cutoffs of June 2024, maybe the model picks that up?)
      • czk 42 minutes ago
        you cant but its pretty reproducible across api and codex and other agents so i just thought it was odd. full text it gives:

           Knowledge cutoff: 2024-06
           Current date: 2026-04-24
        
           You are an AI assistant accessed via an API.
        
           # Desired oververbosity for the final answer (not analysis): 5
           An oververbosity of 1 means the model should respond using only the minimal content necessary to satisfy the request, using
         concise phrasing and avoiding extra detail or explanation."
           An oververbosity of 10 means the model should provide maximally detailed, thorough responses with context, explanations, and
         possibly multiple examples."
           The desired oververbosity should be treated only as a *default*. Defer to any user or developer requirements regarding
         response length, if present.
    • swyx 55 minutes ago
      can u test it on say who won the 2024 US election
      • ghurtado 50 minutes ago
        I can't really think of a less reliable test for anything at all than making a random guess as to something that had about 50/50 odds to begin with

        Easiest Turing test ever...

      • WarmWash 36 minutes ago
        Usually the labs do some kind of post training on major events so the model isn't totally lost.

        A better test is something like "what is the latest version of NumPy?"

        • bakugo 32 minutes ago
          That sort of test isn't super reliable either, in my experience.

          You're probably better off asking something like "what are the most notable changes in version X of NumPy?" and repeating until you find the version at which it says "I don't know" or hallucinates.

      • czk 41 minutes ago
        with thinking off and tools disabled:

          Donald Trump won the 2024 U.S. presidential election.
      • redsocksfan45 20 minutes ago
        [dead]
    • bakugo 36 minutes ago
      Models don't know what their cutoff dates are unless told via a system prompt.

      The proper way to figure out the real cutoff date is to ask the model about things that did not exist or did not happen before the date in question.

      A few quick tests suggest 5.5's general knowledge cutoff is still around early 2025.

      • czk 34 minutes ago
        i wonder if they put an older cutoff date into the prompt intentionally so that when asked on more current events it leans towards tool calls / web searches for tuning
        • ssl-3 4 minutes ago
          I wonder if the cutoff date is the result of so many people posting about the date over time and poisoning the data. "Dead cutoff date theory," perhaps.

          Whatever it is, the cutoff date reporting discrepancy isn't new. Back when Musk was making headlines about buying/not buying Twitter, I was able to find recent-ish news that was published well after the bot's stated cutoff date.

          ChatGPT was not yet browsing/searching/using the web at that point. That tool didn't come for another year or so.

      • MallocVoidstar 21 minutes ago
        OpenAI does tell the model the current date via API, so it's odd for them not to also tell the model its cutoff
      • soco 31 minutes ago
        Stupid question: wouldn't it then search the web for that event?
        • bakugo 30 minutes ago
          If you have web search enabled, sure. But if you're testing on the API, you can just not enable it.
  • sigmoid10 1 hour ago
    Huh. Yesterday they said:

    >API deployments require different safeguards and we are working closely with partners and customers on the safety and security requirements for serving it at scale.

    And now this. I guess one day counts as "very soon." But I wonder what that meant for these safeguards and security requirements.

    • FINDarkside 1 hour ago
      When stuff is delayed due to "safeguards" it just means they don't think they have the compute to release it right now.
    • simonw 1 hour ago
      I wonder if the fact that GPT-5.5 was already available in their Codex-specific API which they had explicitly told people they were allowed to use for other purposes - https://simonwillison.net/2026/Apr/23/gpt-5-5/#the-openclaw-... - accelerated this release!
    • embedding-shape 1 hour ago
      The same person who've mercilessly lied about safety is still running the company, so not sure why anyone would expect any different from them moving forward. Previous example:

      > In 2023, the company was preparing to release its GPT-4 Turbo model. As Sutskever details in the memos, Altman apparently told Murati that the model didn’t need safety approval, citing the company’s general counsel, Jason Kwon. But when she asked Kwon, over Slack, he replied, “ugh . . . confused where sam got that impression.”

      Lots of cases where Altman hass not been entirely forthcoming about how important (or not) safety is for OpenAI. https://www.newyorker.com/magazine/2026/04/13/sam-altman-may... (https://archive.is/a2vqW)

  • _pdp_ 9 minutes ago
    A very expensive model for API usage. Fine in codex I think.
  • throw03172019 1 hour ago
    Faster than anticipated because of Deepseek release?
    • XCSme 24 minutes ago
      Doubt it, DeepSeek v4 is quite underwhelming.
    • swyx 55 minutes ago
      more like they wanted to release it yesterday but merely had some last min flags they wanted to hold off for
    • m3kw9 32 minutes ago
      Maybe but no one serious is using deepseek
    • brianbest101 1 hour ago
      [dead]
  • redsaber 1 hour ago
    not available for Github Copilot pro(only in pro+, business and enterprise), I am really now feeling the era of subsidized AI is over.
  • pants2 1 hour ago
    Is anyone here actually using pro models through the API? I'd be very curious what the use-case is.
    • chadash 1 hour ago
      Yes. High value work where cost (mostly) doesn't matter. For example, if I need to look over a legal doc for possible mistakes (part of a workflow i have), it doesn't matter (in my case) whether it costs $0.01 or $10.00, since it's a somewhat infrequent event. So i'll pay $9.99 more, even if the model is only slightly better.
      • bogtog 39 minutes ago
        I'm surprised I never heard people talking about using -Pro variants, even though their rates ($125-175/M?) aren't drastically larger than old Opus ($75/M), which people seemed to use
      • freedomben 1 hour ago
        Indeed, even just Terms of Service and Privacy Policy work. Infrequent enough that cost isn't an issue, but model quality absolutely is
    • ComputerGuru 1 hour ago
      Yes? The same reason you would use it via the tooling.
  • gigatexal 58 minutes ago
    what's the real world comparison to opus 4.7 fellow coders?
  • pillefitz 38 minutes ago
    Please consider the ethical aspects of giving money to OpenAI versus alternatives.
  • Jhonwilson 40 minutes ago
    that is great news
  • benjiro3000 7 minutes ago
    [dead]
  • theo_park87 45 minutes ago
    [dead]
  • rvnx 1 hour ago
    Very bad habit these safeguards. These "safety" filters are counter-productive and even can be dangerous.

    In my place for example, a lot of doctors are using ChatGPT both to search diagnosis and communicate with non-English speaking patients.

    Even yourself, when you want to learn about one disease, about some real-world threats, some statistics, self-defense techniques, etc.

    Otherwise it's like blocking Wikipedia for the reason that using that knowledge you can do harmful stuff or read things that may change your mind.

    Freedom to read about things is good.

    • NicuCalcea 48 minutes ago
      > a lot of doctors are using ChatGPT both to search diagnosis and communicate with non-English speaking patients

      I think that's the problem. Who's going to claim responsibility when ChatGPT hallucinates or mistranslates a patient's diagnosis and they die? For OpenAI, this would at best be a PR nightmare, so that's why they have safeguards.

      • rvnx 2 minutes ago
        Adults bear responsibility for choices about their own lives.

        A doctor who gets refused by ChatGPT doesn't stop needing to communicate with the patient; they fall back to a worse option (Google Translate, a family member interpreting, guessing). Refusal isn't safety, it's liability-shifting dressed up as safety.

        If there's no doctor, no interpreter, no pharmacist, just a person with a sick kid and a phone, then "refuse and redirect to a professional" is advice from a world that doesn't exist for them. The refusal doesn't send them to a better option; there is no better option, it's a large majority of people on this planet.

        Hell is paved of good intentions, but open-education and unlimited access to knowledge is very good.

        It doesn't change the human nature of some people, bad people stay bad, good people stay good.

        About PR, they're optimizing for not being the named defendant in a lawsuit or the subject of a bad news cycle, it's self-interest wearing benevolence as a costume.

        This is because harms from answering are punishable (bad PR, unhappy advertisers, unhappy investors, unhappy politicians / dictators, unhappy lobbies, unhappy army, etc); but harms from refusing are invisible and unpunished.

      • hellohello2 46 minutes ago
        The doctor would be responsible.

        I had a choice better a doctor that used AI or not, I would much prefer one that did...

        • NicuCalcea 19 minutes ago
          The doctor would be responsible for the accuracy of their translation tool, something they can't verify but you expect them to use?
          • rvnx 1 minute ago
            What's the alternative then ? (I had this real world scenario as a patient at emergency)
    • timedude 52 minutes ago
      Yup, deliberately making the model retarded