Why do they bother creating effort to market all these different models.

All I want to know is how old is the model and how much does it cost. I can figure out which one I want to use based on that, assuming that newer models are always better.

Trying to convince us there is a difference between GPT-6-Sol and GPT-5.6-Terra or whatnot is ludicrous to the point of being insulting, especially when new models come out every week.

▲

ecshafer a day ago | parent | next [-]

price discrimination. They want to capture low and high cost agent requests, and different workflows.

▲

ravenstine a day ago | parent | prev [-]

Seriously! Though I prefer GPT models to other frontier models, this shit is confusing. They keep changing the names of these models and they often don't communicate anything meaningful about the model itself, especially with these latest iterations. At least with "mini" and "nano" you understood they generally had differing speeds and "reasoning" capability, but what the hell do "Terra", "Sol", and "Astra" really mean? Which one of them is the effective successor to gpt-5.4-mini? It's hard to tell since the only objective information you'll get is token pricing. Is Terra less capable than Luna because it makes me think of dirt and grass? Or is Luna less powerful because the Earth is bigger than the Moon? Apparently that's the real answer. And why do I even have to think about this? And what comes after Astra? Galactica? Or will they start naming the succeeding models after different candy bars? Should I even care since a new model will get farted out mere days after I figured out what differentiated the last one?

What's unclear to me is who OpenAI thinks they're marketing to with this form of branding. These different models don't really mean all that much to the vast majority of people using their products who aren't developers, and developers aren't helped at all by the way they've been naming said models. Are they merely scared that they'll become irrelevant because Anthropic decided to give their models quirky names like "Opus" and "Fable"?

If OpenAI really wants to give their models names, they should name the generation of model and then have the different sub-models named by purpose or capability level. After all, I wouldn't use Mini for a job that Nano could easily do, and I wouldn't use Nano for a job that the full version of GPT-* necessitates. Similarly, I've had to discover exactly how Luna, Terra, and Sol are appropriate for different complexities and task types. OpenAI could help me skip a lot of those steps and just tell me what each model distillation is good for without causing me to look through their pricing page and make educated guesses. After all, shouldn't they not want me to pay attention to how much they're charging me?

All of this makes the days of frontend framework churn seem quaint and actually preferable.

▲

wyre a day ago | parent [-]

What models are good at is so subjective it isn't OpenAI's place to really say "Use Sol for X and Luna for Y". They are publishing benchmarks so you can figure out how to best utilize each model. I get that it sucks to have to do this yourself, but eventually there will probably be some type of benchmark that help with discovering a model's strengths and weaknesses

The issue that OpenAI had when they had mini and nano models is that ambiguous the differences between those and everyone just used the base model anyway. I have no idea what type of job mini can do that nano couldn't or vis-à-vis.

I do wonder if it would just be better if they were named 6-small, 6, and 6-big?

	▲	ravenstine a day ago \| parent [-]
		> I have no idea what type of job mini can do that nano couldn't or vis-à-vis. In my experience, Nano won't reliably handle complex open-ended tasks and is mostly suited for very explicit instruction that it can't screw up. It's no different from how there are some chores you can give to kids and there are other tasks you need at least a teenager for. If the decision tree of the task is very clear and conventional, Nano can be cheaper than giving the task to a relatively overpowered model, especially if it's something where the output is rigidly structured. This makes it well suited for skills that essentially run CLI commands and generate output, especially because it is usually faster. Mini is more like a discount version of the base model, and Nano is the dollar store version. Mini is more of a generalist and a fairly good deal if you have a moderately complex task that is conventional, but can be less conventional that what Nano can handle. I mostly used gpt-5.4-mini this year for my side projects because it's a pretty good generalist while significantly saving on costs. It is, however, somewhat dumber than the base model and more prone to ignore or forget rules you give it. I'd have just used a base model, but the low cost of Mini and Nano made them appealing to me. Maybe I'm a cheapskate, but I have hundreds or possibly thousands more in my pocket than many other users because of that. This workflow I settled into with Mini and Nano didn't map cleanly on to the current generation of model tiers. With the price of Luna, you'd think it would be a replacement for Nano. In a sense it is, yet I didn't find that Terra became the new Mini. Terra is more powerful, better at explaining its own decisions, yet I've also found it to be relatively stupid while charging me more to use it. On the other hand, Luna with its reasoning set to "high" is what I consider to fill the role of Mini, and is good enough such that I no longer use Mini. Sol and Astra are great, but they're pricey. It could be my own brain and its bad perception, but so far I don't get the point of Terra. Luna succeeded at reverse engineering some abandonware with a very complicated licensing and virtualization scheme, and did so over SSH into a Windows VM with only PowerShell on the other end. Terra did such idiotic crap to my flashcards app that I stopped using it for anything after that. This is why I find OpenAI's naming unhelpful and kind of pointless. I don't really care about the benchmarks that all these models are commonly run against. They're not that useful, IMO. OpenAI could easily give early access to these models, get a ton of feedback, and provide better insight to customers on how these things behave. Even calling Terra "gpt-5.6-overpriced-cheating-dumbass" would be better than wasting my time and money figuring it out myself. But that wouldn't make OpenAI as much money.