# Sebastian Raschka's history of text classifiers

By Saurabh Kumar · TIL note, Oct 10, 2026 · Tags: llm

Source: https://saurabh-kumar.com/til/1791633601/

[Sebastian Raschka's history of text classifiers](https://magazine.sebastianraschka.com/p/classifier-history-and-jev) puts numbers on why [Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev) feels new. On IMDb, bag-of-words + logistic regression gets 89.9%, a fine-tuned ModernBERT about 95%, and Jev 96.5% zero-shot for $0.65 across 25k reviews. Under the hood it is likely still a pretrained transformer with a one-number head that scores each answer option. The hard part is broad training data and calibrated probabilities. What changes is the cost of starting: no labelling, training or hosting per task. Specialists still win on huge volume, the last point of accuracy, or data that can't leave your network. Within a month [OpenAI](https://developers.openai.com/api/docs/guides/decisions) and [Microsoft](https://commandline.microsoft.com/microsoft-decision-1-model-foundry/) shipped the same yes/no, choice and score contract.