, I’ll give my first impressions of the latest OpenAI mannequin, GPT-5.6. The mannequin was launched a number of days in the past, and I’ve gotten the prospect to check it extensively for the reason that launch and evaluate it in opposition to different fashions akin 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 attainable with it. I consider it’s a mannequin with some professionals and a few cons in comparison with the choice Anthropic fashions akin to Opus 4.8 and Fable 5. However general, it’s an excellent mannequin, and I positively advocate making an attempt it out.
Why use GPT-5.6?
To begin with, I’d wish 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 technology of the identical mannequin, GPT-5.5, was a fantastic mannequin and a mannequin I personally used extensively.
I consider GPT-5.5 was mainly on par with Opus 4.8 in a number of duties, and in some duties, akin to code overview, it was far superior for my part.
Thus, you need to after all care in regards to the subsequent technology 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 positively learn about. For instance, the mannequin is available in three completely 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 completely different reasoning ranges, which might make the mannequin suppose for longer or shorter earlier than offering solutions. The straightforward trade-off is that in the event you make the mannequin purpose for longer, it is going to give higher-quality responses, however it is going to take longer to offer responses.
I’ll share my methods and ideas on find out how to use the fashions as successfully as attainable.
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 mainly each facet. It’s only a bit higher than GPT-5.5 for every little thing.
I after all use the mannequin for code opinions, during which it nonetheless discovers a number of points. I consider 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 truly being right when reporting a bug, which is precision.
I’ve additionally tried the mannequin for precise implementations, and I consider GPT-5.6 is ready to work for longer to finish duties and is mainly extra thorough in the best way it does its work. I nonetheless consider GPT-5.5 was fairly good at getting duties achieved, however I feel GPT-5.6 is barely higher.
Nevertheless, it’s price noting that I don’t suppose it is a very robust enchancment; I consider it’s an incremental enchancment over the earlier GPT mannequin.
One draw back I wish to be aware is that in the event you use GPT-5.6 with further excessive and even extremely considering, it mainly drains your utilization limits instantly.
Now it’s price noting that OpenAI really eliminated the five-hour utilization restrict, a minimum of for a brief period of time, which positively helps loads right here. So that you solely have the weekly restrict; nevertheless, I consider that in the event you use the mannequin with further excessive or ultra-thinking, it mainly drains your utilization instantly, and in the event you’re on a subscription, it’s very laborious to make use of the mannequin for an prolonged time period, and positively very laborious to make use of a number of fashions in parallel.
Moreover, I feel that in the event you use the mannequin with considered one of these excessive reasoning modes, it’s additionally very, very sluggish. Slower than I’d count on it to be, positively when engaged on easier 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 price noting that I needed to tune down the reasoning ranges to keep away from hitting charge limits instantly.
That is, after all, vital as a result of whenever you take a look at the benchmarks, what’s reported is often one of many tremendous reasoning ranges, and in the event you’re not in a position to make use of that as a result of it drains your utilization instantly, then that after all makes the mannequin successfully worse for you when making an attempt it in comparison with the benchmarks.
I’d additionally wish to have a brief part masking my ideas on the completely different sizes which you can select. I principally use Sol, the biggest mannequin, as I consider it’s one of the best mannequin. Nevertheless, I’ve learn some benchmarks saying that in some conditions you’re higher off utilizing Terra with a better 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.
The right way to successfully apply GPT-5.6 to unravel issues
Use circumstances for GPT-5.6
Now I’ll get into find out how to successfully use GPT-5.6 to unravel issues. The primary factor you need to begin doing instantly, particularly in the event you’re utilizing Claude Code, is to have GPT carry out your code opinions.
In my view, you principally don’t want human code opinions anymore. After all, you may want it if there’s a vital piece of infrastructure otherwise you actually need a human to take a look at it, however for essentially the most half, I consider that Codex is nice sufficient as a code reviewer to keep away from bugs being pushed to manufacturing.
Now you can even, after all, use GPT-5.6 for precise implementations. Nevertheless, for my part, I’ve higher success utilizing the next setup for implementations. The first step is that I take advantage of Claude Fable to plan the implementation, and step two is that I change and begin executing the implementation with Claude Opus 4.8 as an alternative. In my view, this offers me higher outcomes than simply utilizing GPT-5.6, even when I take advantage of a better reasoning degree for planning after which a decrease reasoning degree for implementations.
And one other level you may use GPT-5.6 for is pc use or browser use. In my view, GPT is excellent at pc use and browser use, and it’s fairly quick when interacting with the browser, particularly if I take advantage of a medium reasoning degree. I feel GPT-5.6 navigates my browser extremely properly, which is, after all, vital when verifying code end-to-end, for instance, or performing actions within the browser for you. So I consider it is a excellent use case.
Strategies to make use of GPT-5.6 successfully
Now, I’ll transfer over to some particular methods that I implement and apply when using GPT-5.6. The primary subject I wish to cowl is the reasoning ranges. As I discussed earlier, in the event you go along with the additional excessive or ultra-reasoning ranges, I consider the mannequin is each too sluggish and spends utilization limits approach too quick, which doesn’t actually work in the event you’re on the subscription, even in the event you’re on the $200 subscription.
Thus, the approach 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 usually simpler than code planning. It’s because code planning requires you to look into all the repository and think about how one thing needs to be applied, whereas the precise implementation is simply implementing the plan that was already made for you.
One other crucial approach when utilizing GPT-5.6 is giving it entry to every little thing. One factor that I seen that was fairly inconvenient was that I’ve labored principally with Claude Code earlier than and had given Claude entry to every little thing I’m utilizing by means of MCP, akin to Gmail, Google Calendar, Slack, Playwright MCP, and so on. After which once I began utilizing GPT-5.6, it carried out worse as a result of I didn’t keep in mind to present it entry to all of those instruments. So my different foremost tip right here is to really present GPT-5.6 entry to all of the instruments that it wants.
OpenAI has mainly all the identical connectors that Claude Code has, and there’s no purpose you shouldn’t give entry to Codex in the event you already give entry to Claude Code.
And lastly, the final tip I wish to cowl is to keep in mind that OpenAI usually offers out resets, which is without doubt one of the massive variations between Claude Code and Codex. So, with Claude Code, they generally do resets of utilization limits for everybody, which is, after all, nice in the event you’ve spent a few of your limits; nevertheless, Codex additionally does that, however they often really present you a banked reset, which is mainly a reset which you can set off at any cut-off date and can reset your utilization limits.
This may be nice if in case you have excessive anticipated utilization for a shorter time, or in the event you simply spent all of your tokens and have to spend extra tokens. Nevertheless, it’s price noting that resetting the utilization limits not solely, after all, 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 good thing about the banked resets, although they’re nonetheless very precious, after all.
Traditionally, OpenAI has offered banked resets from time to time, so if in case you have a subscription, you’ll get them over time.
Conclusion
On this article, I lined my opinion on the most recent OpenAI mannequin, GPT-5.6, and my ideas on it. I mentioned why you need to use the mannequin, highlighting that the earlier technology of the OpenAI mannequin, GPT-5.5, was already excellent, and that that is an enchancment over the mannequin. I additionally shared some particular methods on find out how to use the mannequin successfully, which is essential as a result of GPT-5.6 comes with some completely different utilization settings. For instance, it is available in three completely different sizes of fashions, they usually even have completely different reasoning ranges you’ll be able to select between. I consider you ought to be utilizing GPT-5.6 for code opinions, positively. And the distinction between GPT-5.6 and Opus 4.8 is just not that massive on the subject of code implementations, pc 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. After all, you need to at all times keep on prime of the most recent fashions, attempt them out your self, see in the event that they work higher to 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
