Uncheatable Eval

Rolling perplexity on monthly snapshots of new Wikipedia, GitHub, BBC, arXiv, bioRxiv and AO3 text, meant to limit train-set leakage.

Also known as: UncheatableEval, UE

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorygeneration
Subcategoryrolling log-likelihood / bits-per-byte on newly published web documents
Page statusactive
Metricbits_per_byte (also word_perplexity and byte_perplexity)
Directionlower_is_better
Unitbpb
Dataset size7500
Dataset licenceMIT on the evaluation code (Jellyfish042/uncheatable_eval). The 2026-07 Hub card states no dataset licence.
PublisherJellyfish042

What it measures

Uncheatable Eval does not ask questions. It scores how well a causal language model assigns probability to documents published after typical training cutoffs: new Wikipedia pages, GitHub files, BBC news, arXiv and bioRxiv papers, and AO3 fiction. The publisher argues that a public static QA set can leak into training, while last-week's crawl cannot already be in a released checkpoint. lm-eval implements the upstream rolling log-likelihood over a pinned Hub snapshot. The README says the method is for base models, not chat-tuned ones.

Task format

output_type loglikelihood_rolling. doc_to_text is empty; doc_to_target is the document content field. Fifteen category tasks filter the snapshot on the category column. Group uncheatable_eval averages word_perplexity, byte_perplexity and bits_per_byte weighted by size. Lower is better for all three.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub