#Guide to /aicg/ model naming autism

**%green% GPT %% and %tan% Claude %%**
OpenAI's %green% **GPT** %% and Anthropic's %tan% **Claude** %% are the 2 primary models used by /aicg/. These are not singular models, but rather brands that have had multiple models.
When /aicg/ users refer to %green% **GPT** %% or %tan% **Claude** %%, they are either referring to all of the models or the most recent and relevant model.
For further ease of reading, all %green% **GPT** %% models will be named in %green% **green** %%, and all %tan% **Claude** %% models will be named in %tan% **tan** %%, matching the color schemes of the companies.

%green% **Turbo** %%
%green% **gpt-3.5-turbo** %% is a GPT3 model made to go faster and be cheaper, hence the name.
It is referred to as %green% **Turbo** %% for straightforward reasons.
This was the first GPT model to be particularly relevant on /aicg/.

%green% **GPT4** %%
%green% **gpt-4** %% is the model of GPT released after Turbo.
It's referred to as %green% **GPT4** %% with any variant of capitalization and punctuation.
There are several variants of GPT4, including:
%green% **gpt-4** %%
%green% **gpt-4-0314** %%
%green% **gpt-4-0613** %%
%green% **gpt-4-32k** %%
%green% **gpt-4-32k-0314** %%
%green% **gpt-4-32k-0613** %%
The 32k models distinguish themselves by having a higher context limit. In the context of bragging about model access, assume it's not 32k unless specified. In the context of writing style, 32k is dumber.
The 0613 models are more recent than the 0314 models and are considered the default. Unless specified that the user is referring to 0314, assume it's 0613.
32k and 0314 are depreciated now. If someone refers to GPT4 in a new thread, they are almost certainly referring to **gpt-4-0613**.

%green% **Furbo** %%
%green% **gpt-4-turbo** %% is a GPT4 model made to go faster and be cheaper, hence the name. Other models referred to as %green% **Furbo** %% are %green% **gpt-4-1106-preview** %% and %green% **gpt-4-1025-preview** %%.
%green% **Furbo** %% may be referred to as %green% **non-preview** %% if it's not one of the versions ending in "-preview".
This is the first model with a nickname that may not make intuitive sense.
It is referred to as %green% **Furbo** %%, taking the "F" in "four" and the "urbo" from "Turbo".
%green% **4urbo** %% was a contender for a nickname, and while it ultimately lost, most /aicg/ users will understand what you mean.

%green% **Vurbo** %%
%green% **gpt-4-vision-preview** %% is a GPT4 model that can interpret images.
Its nickname is %green% **Vurbo** %%, with the "V" from "vision" and "urbo" from "Turbo".
The vision aspect or %green% **Vurbo** %% is mostly irrelevant because most proxies disable the sending of images. %green% **Vurbo** %% was instead sought after because non-preview Furbo came with vision enabled.

%green% **Orbo** %%
%green% **gpt-4o** %%, otherwise known as GPT-4 Omni.
It's called %green% **Orbo** %%, with the "O" from "omni" and the "rbo" from "Turbo".
%green% **4omni** %% and simply %green% **Omni** %% are also accepted names.

%green% **Chorbo/Larbo/Lorbo/Latest** %%
%green% **chatgpt-4o-latest** %% and %green% **gpt-4o-08-06** %% are the most recent additions to the GPT family. Despite being different models, they are frequently referred to interchangeably.
Due to their recency, a name has yet to be fully settled on.
%green% **Chorbo** %% takes the "Ch" from "chatgpt", and adds it to "Orbo".
%green% **Larbo** %% takes the "La" from "latest", and "rbo" from "Turbo".
%green% **Lorbo** %% only takes the "L" from "latest", and adds it to "Orbo".
%green% **Chato** %% takes the "Chat" from "chatgpt" and the "o" that "Omni" starts with and "Turbo" ends with.
%green% **Latest** %% is the most clear but least creative name.
%green% **nu4o** %% and %green% **nuomni** %%, because 08-06 is the new 4o/Omni.
This rentry will be updated if/when a final nickname is decided upon.

%tan% **Claude** %%
Claude has multiple variants that are simply referred to as %tan% **Claude**. %%
These versions are: %tan%  **1.0** %%, %tan% **1.1** %%, %tan% **1.2** %%, %tan% **1.3** %%, %tan% **2.0** %%, and %tan%  **2.1.** %%
At the time of this rentry's most recent update, 2.1 is the most recent model of Claude that's almost exclusively referred to as simply %tan% **Claude**. %% Earlier models are referred to by their number, and later models are referred to by different nicknames.
2.1 is severely outdated, but still relevant enough in droughts that %tan% **2.1** %% doesn't always require specification.
If a user is referring to access to a specific model and says %tan% **Claude** %%, assume they mean %tan% **2.1** %%.
If a user is referring to %tan% **Claude** %% as a whole, then assume that it's all of the models.

%tan% **Claude 3.0** %%
Claude 3.0 came in 3 different models, which each had nicknames given by Anthropic themselves.
Because there are 3 models of Claude 3.0, simply calling it "Claude 3.0" is insufficient for most purposes.
%tan% **claude-3-haiku** %%, the cheapest but dumbest. This is called %tan% **Haiku** %%.
%tan% **claude-3-sonnet** %%, the middle child. This is called %tan% **Sonnet** %%.
%tan% **claude-3-opus** %%, the smartest but most expensive. This is called %tan% **Opus** %%.
When speaking exclusively about one of these models, expect /aicg/ users to specify which one they refer to.

%tan% **Sorbet** %%
%tan% **claude-3.5-sonnet** %% is the most recent edition to the Claude family. It's a more intelligent version of Sonnet.
It's not a completely unique model, but an update to an old one, the same way Orbo was for GPT4.
As such, it's referred to as %tan% **Sorbet** %%, taking the "onn" out of "Sonnet" and replacing it with the "orb" from "Orbo".
%tan% **Sorbet** %% is pronounced the same way as the dessert despite the etymology.