Cutoff Bench: How outdated is the training data of major LLMs

(franciscocarloserra.github.io)

3 points | by FranciscoCarlos 5 hours ago ago

3 comments

  • causal 5 hours ago ago

    Useful, and I like reported vs. remembered difference. Would be nice to have a larger selection of models, including other modalities.

    • FranciscoCarlos 5 hours ago ago

      Willing to scale it up if there's interest

  • FranciscoCarlos 5 hours ago ago

    Also a great potential indicator on when the pretraining run for the model started.