CC-Bench-V2 Repo Exploration

coding

Multilingual: no

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

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: agents, coding. Language: en. Verified by llm-stats: no.