agents benchmark
Kimi Code Bench v2
Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
Kimi Code Bench v2 Ranking
Higher score ranks better on this benchmark.
| 01 | MA | 72.9% | 100.0% | 2 | C | |
| 02 | MA | 62.0% | 0.0% | 2 | C |
Kimi Code Bench v2 Score Distribution
A closer view of the leading scores on this benchmark.
Kimi Code Bench v2 Highlights
The leading models and scores on this benchmark.
What is Kimi Code Bench v2?
What Kimi Code Bench v2 measures and how its scores work.
Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Kimi Code Bench v2
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- kimi-code-bench-v2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Kimi Code Bench v2.
Which model scores highest on Kimi Code Bench v2?
Kimi K3 is currently ranked first with 72.9%.
What does Kimi Code Bench v2 measure?
Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.