Pith. sign in

← back to paper

Review history

arxiv: 2606.11864 · 2 revisions

CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding

  1. 2026-07-14 CONDITIONAL HIGH v1.1.0-grok45 novelty 7.0
    33913 ms 46711 in 3214 out 2026-07-14T18:02:58.739745+00:00
  2. 2026-06-27 ACCEPT LOW v0.9.1-grok novelty 7.0
    17720 ms 5736 in 1055 out 2026-06-27T08:23:35.058292+00:00