Kimi Code Bench 3.0 Long-horizon

Kimi Code Bench 3.0 Long-horizon is a benchmark for how well a model works as an autonomous coding agent. The official description says: "Internal Moonshot long-horizon coding benchmark; Kimi tested with Claude Code, competitors at max effort with possible fallback behavior". Below we describe in simple words what benchmarks of this type generally examine.

Kimi Code Bench 3.0 Long-horizon measures how well a model works as an autonomous coding agent. In detail, it checks:

• fixing real, open bugs from real software repositories
• planning multi-step changes, running commands and editing files by itself
• passing the project's test suite after its changes
• handling whole repositories, not just small isolated code snippets

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Internal Moonshot long-horizon coding benchmark; Kimi tested with Claude Code, competitors at max effort with possible fallback behavior.

What is the Kimi Code Bench 3.0 Long-horizon benchmark?

Kimi Code Bench 3.0 Long-horizon is a benchmark for how well a model works as an autonomous coding agent. The official description says: 'Internal Moonshot long-horizon coding benchmark; Kimi tested with Claude Code, competitors at max effort with possible fallback behavior'. Below we describe in simple words what benchmarks of this type generally examine.

What does Kimi Code Bench 3.0 Long-horizon test?

Kimi Code Bench 3.0 Long-horizon mainly measures how well a model works as an autonomous coding agent. Concretely, it checks: fixing real, open bugs from real software repositories; planning multi-step changes, running commands and editing files by itself; passing the project's test suite after its changes.

How is the Kimi Code Bench 3.0 Long-horizon score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get Kimi Code Bench 3.0 Long-horizon data and scores?

The official source is https://huggingface.co/moonshotai/Kimi-K3.1-Pro. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/kimi-code-bench-3-0-long-horizon/scores) or pull it directly from the Open LLM Radar API with any HTTP client.