Kimi Hallucination Benchmark without tools (Internal) (Kimi Hallu Bench)
We show this table for reference; we do not rank on it.
Moonshot AI's internal factuality benchmark built from challenging, de-identified prompts drawn from practical work tasks, scored as the claim-level hallucination rate.
Benchmark score on Kimi Hallu Bench — October 29, 2026
We compile the Kimi Hallu Bench rows from provider self-reports. Kimi K3.1 Pro leads the table at 5.4%. We do not use these results to rank models overall.
1 modelKnowledgeCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (1 model)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Kimi K3.1 ProMoonshot AI | 5.4% | Not reported | Pending |
About Kimi Hallu Bench
Year
2026
Tasks
Internal work-task prompts without tools
Format
Claim-level hallucination rate
Difficulty
Factuality stress test
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.
Freshness and provenance
Version
Kimi Hallu Bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
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.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.