Segue
Segue
Today
iOS
Evaluation & Observability·Artificial Intelligence
benchmark saturation

benchmark saturation

/ˈbentʃmɑːrk ˌsætʃəˈreɪʃən/

📏 Evaluation & Observability

when models max out a test so it can no longer tell them apart

benchmark saturation in a sentence

“Benchmark saturation forced the lab to commission a harder eval.”

Origin of benchmark saturation

benchmark: a surveyor's mark cut in stone + Latin saturare to fill

Related Words

observability

the degree to which a system's inner behavior can be inferred from what it emits

verbosity bias

a judge's tendency to score longer answers higher regardless of quality

evals

systematic tests to measure model performance on specific tasks

LLM-as-a-Judge

using a strong LLM to evaluate the outputs of another model

ground truth

the actual absolute truth or correct answer used for comparison

tracing

recording the flow of execution and data through a complex system

SegueMaster the art of eloquence
iOS AppWord of the DayBlogContactPrivacyTerms
English简体中文日本語한국어Español