Fig.1

Concept

Pass@4

pass@k is an evaluation metric that reports the probability that at least one of k independently sampled attempts solves a given problem. pass@4 is the special case where the model gets four tries, and the task counts as solved if any one of them passes the checker (unit…

The rest of “Pass@4” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Pass@4, explained · Fig. 1