Benchmark

Long Code Arena

A code understanding benchmark dataset used to evaluate the ability of models to understand and reason over long code contexts.

Timeline (last 90 days)

Oct 20

KV-Surgeon was evaluated on three long-context benchmark datasets: QuALITY, LongHealth, and Long Code Arena.

Unverified50%

KV-Surgeon was evaluated on three long-context benchmark datasets: QuALITY, LongHealth, and Long Code Arena.