Ted Sanders 解释 OpenAI 模型命名规则：6.1 与 7 有何区别
Quoting Ted Sanders
OpenAI 员工亲口讲清模型版本号怎么读，看完你就知道 6.1 和 7 差在哪了。
OpenAI 的 Ted Sanders 在 Simon Willison 的博客中解释了模型命名逻辑。他说明 OpenAI 模型按规模排序为 Luna、Terra、Sol、Astra 四档，更大的模型性能更可靠但每 token 成本更高。版本号同时表示发布顺序、与其他版本的关系和改进幅度：例如 6.1 表示晚于 5.6 发布、与 6.1 系列共享训练数据和风格，但提升幅度不足以称为 7。
Quoting Ted Sanders
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
