Why this is here: SOURCE-BACKED + 95 signal strength + high ranking score + source-backed + fresh within 24h.
VQV Signal
SOURCE-BACKED
95% signal strength
RuBench 1.0: Benchmark for Russian-Language Agentic Coding Tasks
RuBench 1.0 introduces a benchmark of 25 tasks based on real fix commits with native Russian task specifications, addressing the gap in repository-level agentic coding benchmarks that use only English. It reflects developers' use of product-grade coding agents handling maintenance tasks stated in t...
This benchmark better represents real-world coding scenarios where developers issue tasks in their native language, enabling more relevant evaluation of coding agents beyond English-only settings. It supports the development of AI coding tools that can understand and act on non-English, customer-st...
AI-assisted summary based on listed sources.
Score 80
Source Type arxiv
Reposts 0
Topic Quality 66
Open the original source for full context, or open the topic page to see related signals and the topic timeline.