Ted Sanders 解释 OpenAI 模型命名规则：Luna < Terra < Sol < Astra
Quoting Ted Sanders
OpenAI 的 Ted Sanders 解释其模型命名规则：模型按 Luna < Terra < Sol < Astra 排序，规模越大性能与可靠性越高、每 token 成本越高、对冷门事实的召回越好。版本号同时表示发布顺序、与其他版本的关系和改进幅度，如 6.1 在 5.6 之后发布、与同代 6.1 模型共享训练数据和风格，但提升幅度不足以称为 7。
In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable: model size. In general, models that are bigger will (a) be more performant / reliable, (b) cost more per token, and (c) have better recall of esoteric facts. As you note, our models are ordered:
Luna < Terra < Sol < Astra
[...] These days, version number signifies a few things at once: the order of release, the relationship to other releases, and the magnitude of improvement. So something like 6.1 would indicate it was launched after 5.6, may share some similarities to other 6.1 models in terms of training data / personality (which is why it's not 5.7), and isn't a giant enough leap to merit the headlines and expectations that would come with a 7.
— Ted Sanders, explaining OpenAI's model naming conventions
Tags: generative-ai, gpt, openai, ai, llms, ted-sanders
来源：Simon Willison 博客 · simonwillison.net