Pith. sign in

← back to paper

Review history

arxiv: 2607.20911 · 2 revisions

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

  1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
    122457 ms 24600 in 14985 out 2026-08-15T15:31:08.260108+00:00
  2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
    62453 ms 24542 in 7527 out 2026-08-01T09:00:06.801226+00:00