← back to paper

Review history

arxiv: 2607.06411 · 2 revisions

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications

1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 8.0
   183090 ms 17195 in 21399 out 2026-08-02T08:16:10.681983+00:00
2. 2026-07-08 CONDITIONAL MODERATE v1.1.0-glm novelty 7.0
   331006 ms 17767 in 3166 out 2026-07-08T06:32:29.589638+00:00