Benchmark
RuBench
What is RuBench?
Evaluates coding agents on 25 repository-level tasks in Russian, mined from recent fix commits across five open-source projects. Graded by upstream regression…
- Released
- 2026-07-07
- Evaluates
- Code & Software, Software & AI Compute, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2607.06411
RuBench paper and code
No reported scores are on record for this benchmark yet.