# Kimi Hallucination Benchmark without tools (Internal) (Kimi Hallu Bench)

> Moonshot AI's internal factuality benchmark built from challenging, de-identified prompts drawn from practical work tasks, scored as the claim-level hallucination rate.

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

- Category: [Knowledge](/knowledge)
- Last updated: October 29, 2026

## About Kimi Hallu Bench

- Year: 2026
- Tasks: Internal work-task prompts without tools
- Format: Claim-level hallucination rate
- Difficulty: Factuality stress test
- Paper: [Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence](https://www.kimi.ai/blog/kimi-k3-1-pro)

Fact-checking agents judge each factual claim in a response; the reported value is the share of claims that contain errors, so lower is better. Moonshot describes the set as a stress test that does not represent everyday error rates. BenchLM stores the provider-published internal benchmark value as display-only launch evidence and does not treat it as an independently reproducible score.

Kimi Hallu Bench 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 | 5.4% |

## FAQ

### What does Kimi Hallu Bench measure?

Moonshot AI's internal factuality benchmark built from challenging, de-identified prompts drawn from practical work tasks, scored as the claim-level hallucination rate.

### Which model scores highest on Kimi Hallu Bench?

Kimi K3.1 Pro by Moonshot AI currently leads with a score of 5.4% on Kimi Hallu Bench.

### How many models are evaluated on Kimi Hallu Bench?

1 AI models have published results on Kimi Hallu Bench in the BenchLM catalog.

### Does Kimi Hallu Bench affect BenchLM's overall score?

Not directly. Kimi Hallu Bench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.