, I’ll give my first impressions of the latest OpenAI mannequin, GPT-5.6. The mannequin was launched a couple of days in the past, and I’ve gotten the possibility to check it extensively for the reason that launch and evaluate it towards different fashions similar to GPT-5.5, Opus 4.8, and Fable 5.
I’ll give my judgment on the mannequin, share my experiences with it, and clarify find out how to work as successfully as potential with it. I imagine it’s a mannequin with some professionals and a few cons in comparison with the choice Anthropic fashions similar to Opus 4.8 and Fable 5. However general, it’s an excellent mannequin, and I undoubtedly advocate making an attempt it out.
Why use GPT-5.6?
To begin with, I’d prefer to cowl why you need to care about this text, and on this case, it’s why you need to care about GPT-5.6 and find out how to use it successfully. To begin with, the explanation you need to care about GPT-5.6 is that the earlier era of the identical mannequin, GPT-5.5, was a terrific mannequin and a mannequin I personally used extensively.
I imagine GPT-5.5 was principally on par with Opus 4.8 in a variety of duties, and in some duties, similar to code evaluate, it was far superior in my view.
Thus, you need to in fact care concerning the subsequent era of the identical mannequin, GPT-5.6, because it ought to, on paper, be higher. Moreover, GPT-5.6 has some quirks which you need to undoubtedly find out about. For instance, the mannequin is available in three totally different sizes:
The place Sol refers back to the Solar, Terra refers back to the Earth, and Luna refers back to the Moon, representing the sizes of the fashions. Sol is one of the best one and the frontier mannequin. Additionally they, with every mannequin, launched totally different reasoning ranges, which may make the mannequin suppose for longer or shorter earlier than offering solutions. The straightforward trade-off is that when you make the mannequin cause for longer, it is going to give higher-quality responses, however it is going to take longer to offer responses.
I’ll share my strategies and ideas on find out how to use the fashions as successfully as potential.
My ideas on GPT-5.6
First, let me cowl my general ideas on GPT-5.6. General, I’d say it’s an enchancment over GPT-5.5 in principally each side. It’s only a bit higher than GPT-5.5 for all the pieces.
I in fact use the mannequin for code evaluations, by which it nonetheless discovers a variety of points. I imagine it’s barely higher at catching points within the code, each with regard to precision and recall, i.e., catching all of the bugs that exist, which is recall, and really being right when reporting a bug, which is precision.
I’ve additionally tried the mannequin for precise implementations, and I imagine GPT-5.6 is ready to work for longer to finish duties and is principally extra thorough in the best way it does its work. I nonetheless imagine GPT-5.5 was fairly good at getting duties executed, however I feel GPT-5.6 is barely higher.
Nonetheless, it’s value noting that I don’t suppose it is a very sturdy enchancment; I imagine it’s an incremental enchancment over the earlier GPT mannequin.
One draw back I wish to be aware is that when you use GPT-5.6 with further excessive and even extremely considering, it principally drains your utilization limits instantly.
Now it’s value noting that OpenAI really eliminated the five-hour utilization restrict, a minimum of for a short lived period of time, which undoubtedly helps lots right here. So that you solely have the weekly restrict; nevertheless, I imagine that when you use the mannequin with further excessive or ultra-thinking, it principally drains your utilization instantly, and when you’re on a subscription, it’s very onerous to make use of the mannequin for an prolonged time frame, and undoubtedly very onerous to make use of a number of fashions in parallel.
Moreover, I feel that when you use the mannequin with one among these excessive reasoning modes, it’s additionally very, very gradual. Slower than I’d anticipate it to be, undoubtedly when engaged on less complicated duties. So, I’ve really ended up utilizing further excessive considering for planning and medium reasoning for precise implementations, which I’ll cowl extra within the subsequent part. However I feel it’s value noting that I needed to tune down the reasoning ranges to keep away from hitting charge limits instantly.
That is, in fact, necessary as a result of while you take a look at the benchmarks, what’s reported is normally one of many tremendous reasoning ranges, and when you’re not ready to make use of that as a result of it drains your utilization instantly, then that in fact makes the mannequin successfully worse for you when making an attempt it in comparison with the benchmarks.
I’d additionally prefer to have a brief part protecting my ideas on the totally different sizes that you could select. I principally use Sol, the biggest mannequin, as I imagine it’s one of the best mannequin. Nonetheless, I’ve learn some benchmarks saying that in some conditions you’re higher off utilizing Terra with the next reasoning degree than Sol with the decrease reasoning ranges. I examined this a bit myself and wasn’t actually capable of discover any stark variations, so I ended up staying with Sol with the reasoning efforts that I discussed earlier.
How you can successfully apply GPT-5.6 to resolve issues
Use circumstances for GPT-5.6
Now I’ll get into find out how to successfully use GPT-5.6 to resolve issues. The primary factor you need to begin doing instantly, particularly when you’re utilizing Claude Code, is to have GPT carry out your code evaluations.
For my part, you principally don’t want human code evaluations anymore. In fact, you may want it if there’s a essential piece of infrastructure otherwise you actually desire a human to have a look at it, however for essentially the most half, I imagine that Codex is sweet sufficient as a code reviewer to keep away from bugs being pushed to manufacturing.
Now you may also, in fact, use GPT-5.6 for precise implementations. Nonetheless, in my view, I’ve higher success utilizing the next setup for implementations. The 1st step is that I exploit Claude Fable to plan the implementation, and step two is that I change and begin executing the implementation with Claude Opus 4.8 as a substitute. For my part, this provides me higher outcomes than simply utilizing GPT-5.6, even when I exploit the next reasoning degree for planning after which a decrease reasoning degree for implementations.
And one other level you may use GPT-5.6 for is laptop use or browser use. For my part, GPT is excellent at laptop use and browser use, and it’s fairly quick when interacting with the browser, particularly if I exploit a medium reasoning degree. I feel GPT-5.6 navigates my browser extremely properly, which is, in fact, necessary when verifying code end-to-end, for instance, or performing actions within the browser for you. So I imagine it is a superb use case.
Strategies to make use of GPT-5.6 successfully
Now, I’ll transfer over to some particular strategies that I implement and apply when using GPT-5.6. The primary subject I need to cowl is the reasoning ranges. As I discussed earlier, when you go together with the additional excessive or ultra-reasoning ranges, I imagine the mannequin is each too gradual and spends utilization limits manner too quick, which doesn’t actually work when you’re on the subscription, even when you’re on the $200 subscription.
Thus, the method that I began utilizing is that I’ve further excessive considering once I’m planning with GPT-5.6. So, at all times once I’m beginning a job, I begin with plan mode, which has further excessive reasoning. When the plan is completed, I change to a medium reasoning degree to really implement the code, contemplating code implementation is commonly simpler than code planning. It’s because code planning requires you to look into your entire repository and take into account how one thing ought to be applied, whereas the precise implementation is simply implementing the plan that was already made for you.
One other crucial method when utilizing GPT-5.6 is giving it entry to all the pieces. One factor that I observed that was fairly inconvenient was that I’ve labored principally with Claude Code earlier than and had given Claude entry to all the pieces I’m utilizing via MCP, similar to Gmail, Google Calendar, Slack, Playwright MCP, and so forth. After which once I began utilizing GPT-5.6, it carried out worse as a result of I didn’t bear in mind to present it entry to all of those instruments. So my different predominant tip right here is to really present GPT-5.6 entry to all of the instruments that it wants.
OpenAI has principally all the identical connectors that Claude Code has, and there’s no cause you shouldn’t give entry to Codex when you already give entry to Claude Code.
And lastly, the final tip I need to cowl is to keep in mind that OpenAI typically provides out resets, which is without doubt one of the massive variations between Claude Code and Codex. So, with Claude Code, they often do resets of utilization limits for everybody, which is, in fact, nice when you’ve spent a few of your limits; nevertheless, Codex additionally does that, however they normally really present you a banked reset, which is principally a reset that you could set off at any time limit and can reset your utilization limits.
This may be nice in case you have excessive anticipated utilization for a shorter time, or when you simply spent all of your tokens and must spend extra tokens. Nonetheless, it’s value noting that resetting the utilization limits not solely, in fact, units your utilization to 0%, nevertheless it additionally resets the date of when the following utilization reset happens. So your subsequent five-hour restrict can be 5 hours later, and your subsequent week restrict can be one week later. So in addition they reset, which reduces the advantage of the banked resets, although they’re nonetheless very priceless, in fact.
Traditionally, OpenAI has offered banked resets from time to time, so in case you have a subscription, you’ll get them over time.
Conclusion
On this article, I coated my opinion on the newest OpenAI mannequin, GPT-5.6, and my ideas on it. I mentioned why you need to use the mannequin, highlighting that the earlier era of the OpenAI mannequin, GPT-5.5, was already superb, and that that is an enchancment over the mannequin. I additionally shared some particular strategies on find out how to use the mannequin successfully, which is essential as a result of GPT-5.6 comes with some totally different utilization settings. For instance, it is available in three totally different sizes of fashions, they usually even have totally different reasoning ranges you may select between. I imagine you have to be utilizing GPT-5.6 for code evaluations, undoubtedly. And the distinction between GPT-5.6 and Opus 4.8 shouldn’t be that massive in relation to code implementations, laptop use, and so forth. So my present coding setup will nonetheless stay: Claude Fable for planning, Opus 4.8 for execution, and GPT-5.6 for reviewing my code. In fact, you need to at all times keep on prime of the newest fashions, strive them out your self, see in the event that they work higher on your use circumstances, and thus determine if it’s related to you.
👉 My free eBook and Webinar:
🚀 10x Your Engineering with LLMs (Free 3-Day E mail Course)
📚 Get my free Imaginative and prescient Language Fashions e-book
💻 My webinar on Imaginative and prescient Language Fashions
👉 Discover me on socials:
💌 Substack
