# OpenAI's Ted Sanders explains how its model version numbers signal release order and scale

> Original title: Quoting Ted Sanders

- Source: Simon Willison
- Published: 2026-10-28T23:23:21.000Z
- Bad Influence: https://badinfluence.news/items/rxo4nxatu7he84vjbsxo7r07i
- Original: https://simonwillison.net/2026/Oct/28/ted-sanders/

## Summary

Ted Sanders, an OpenAI researcher, says model size explains much of LLM performance variation, with bigger models being more reliable and costlier per token. He says OpenAI's version numbers signal release order, relation to other releases, and magnitude of improvement, so 6.1 follows 5.6 and is not a major enough leap to be called 7.