Benchmark Radar
AI BENCHMARK PROFILE

CC-Bench-V2 Repo Exploration

General AIAgents

CC-Bench-V2 Repo Exploration evaluates coding agents on repository-level understanding and navigation, measuring ability to explore, comprehend, and work across entire codebases.

Released
Unknown
Readiness
Paper only
Primary field
General AI

Primary resources

Benchmark Radar records only publicly supported details and links back to primary sources for verification.