# Kimi Code Bench 3.0 Long-horizon (Internal) (Kimi Code Bench 3.0 Long-horizon)

> Moonshot AI's internal long-horizon coding-agent benchmark, the successor to Kimi Code Bench 2.0.

Canonical page: https://benchlm.ai/benchmarks/kimicodebench3longhorizon

- Category: [Coding](/coding)
- Last updated: October 29, 2026

## About Kimi Code Bench 3.0 Long-horizon

- Year: 2026
- Tasks: Internal long-horizon coding-agent tasks
- Format: Coding-agent pass rate
- Difficulty: Long-horizon software engineering
- Paper: [Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence](https://www.kimi.ai/blog/kimi-k3-1-pro)

Moonshot evaluates Kimi models with Claude Code harnesses and other models at their max-effort settings, and notes that proprietary-model runs may involve fallback behavior. BenchLM stores the provider-published internal benchmark value as display-only launch evidence and does not treat it as an independently reproducible score.

Kimi Code Bench 3.0 Long-horizon is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | Moonshot AI | 61.2% |

## FAQ

### What does Kimi Code Bench 3.0 Long-horizon measure?

Moonshot AI's internal long-horizon coding-agent benchmark, the successor to Kimi Code Bench 2.0.

### Which model scores highest on Kimi Code Bench 3.0 Long-horizon?

Kimi K3.1 Pro by Moonshot AI currently leads with a score of 61.2% on Kimi Code Bench 3.0 Long-horizon.

### How many models are evaluated on Kimi Code Bench 3.0 Long-horizon?

1 AI models have published results on Kimi Code Bench 3.0 Long-horizon in the BenchLM catalog.

### Does Kimi Code Bench 3.0 Long-horizon affect BenchLM's overall score?

Not directly. Kimi Code Bench 3.0 Long-horizon is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.