Home/Archive/Benchmarks

The archive

48 posts
Showing 1–1 of 1 · #retrieval
Lost in the middle: why long-context models still forget, and how to test itBENCHMARKS

Lost in the middle: why long-context models still forget, and how to test it

Needle tests are easy to pass. Real documents need several facts combined from different places. Here is how to measure long-context recall properly.

MOMira OkaforOct 22 · 6 min

Get the Sunday Diff — every post worth reading, once a week.