agents benchmark
CC-Bench-V2 Repo Exploration
CC-Bench-V2 Repo Exploration evaluates coding agents on repository-level understanding and navigation, measuring ability to explore, comprehend, and work across entire codebases.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
CC-Bench-V2 Repo Exploration Ranking
Higher score ranks better on this benchmark.
| 01 | ZA | 72.2% | 100.0% | 1 | C |
CC-Bench-V2 Repo Exploration Highlights
The leading models and scores on this benchmark.
What is CC-Bench-V2 Repo Exploration?
What CC-Bench-V2 Repo Exploration measures and how its scores work.
CC-Bench-V2 Repo Exploration evaluates coding agents on repository-level understanding and navigation, measuring ability to explore, comprehend, and work across entire codebases.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CC-Bench-V2 Repo Exploration
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- cc-bench-v2-repo|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CC-Bench-V2 Repo Exploration.
Which model scores highest on CC-Bench-V2 Repo Exploration?
GLM-5V-Turbo is currently ranked first with 72.2%.
What does CC-Bench-V2 Repo Exploration measure?
CC-Bench-V2 Repo Exploration evaluates coding agents on repository-level understanding and navigation, measuring ability to explore, comprehend, and work across entire codebases.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.