Kimi Hallu Bench
Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated.
In-house. Moonshot reports a set without tools and a Hard set with tools. Moonshot says the rates are a stress test and not daily error rates.
- Made by
- Moonshot AI
- Released
- October 2026
- Kind
- Hallucination rates
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- GPT-6 Astra #3 on the capability index
- Last in a launch post
- October 2026
- Last model added
- October 2026
- Scores refreshed
- November 12th, 2026
GPT-6 Astra leads with 4.20%
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 GPT-6 Astra without tools 4.20%
- 2 Kimi K3.1 Pro without tools 5.40%
- 3 Claude Opus 5.5 without tools 6.80%
- 4 Claude Fable 5.1 without tools 11.4%
- 5
DeepSeek V4.1 Flash 1017 without tools 13.1% - 6 GLM-5.3 without tools 14.8%
Source: Official Kimi Hallu Bench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 4.20% | without tools | Sep 2026 | Official leaderboard |
| 2 | Kimi K3.1 Pro | 5.40% | without tools | Oct 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 6.80% | without tools | Sep 2026 | Official leaderboard |
| 4 | Claude Fable 5.1 | 11.4% | without tools | Sep 2026 | Official leaderboard |
| 5 | DeepSeek V4.1 Flash 1017 | 13.1% | without tools | Oct 2026 | Official leaderboard |
| 6 | GLM-5.3 | 14.8% | without tools | Aug 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. We plot every source in the charts below.
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Kimi Hallu Bench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Kimi Hallu Bench leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 24, 2026 | Kimi K3.1 Pro | 8.3 | Kimi Hallu Bench Hard w/ tools (Internal, lower is better) |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Kimi K3.1 Pro | 8.30% Kimi Hallu Bench Hard w/ tools (Internal, lower is better) | 5.40% Leaderboard, without tools | −2.9 pts |
More in Factuality
- SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references.
Qwen3.7-Plus 81.7% - HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy.
Keye-VL-2.0-30B-A3B 73.5% - SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge.
Gemini 3.1 Pro 77.5% - Internal adversarially-designed factuality evaluations In use Models answer adversarial questions in nine categories such as history, math and code. Scored on agreement with human ideal responses. GPT-6 Luna 7.60%
- AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones.
Inkling 2 Small 16.1 - GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages.
Nemotron 3.5 Bolt E4B 40.7%