Kimi K3.1 Pro Tech Blog - Kimi Hallu Bench Hard (with tools): leaderboard

Moonshot AI's in-house hallucination stress test on challenging, de-identified prompts drawn from practical work tasks and crafted to probe situations where models are prone to errors; fact-checking agents assess every claim. This is the sheet's Hard set, answered with tools. The score is the claim-level hallucination rate in percent, so lower is better; Moonshot says the rates do not represent overall error rates in daily use. Kimi K3.1 Pro launch post benchmark sheet (October 2026); models at max reasoning effort. Moonshot notes that its proprietary-model runs may involve fallback behavior.

Metric: Claim-level Hallucination Rate (%, lower is better). Source: www.kimi.com.

Interactive version: theaggregate.ai/benchmark?slug=kimi-k3-1-pro-tech-blog-kimi-hallu-bench-hard-with-tools · How It Works · Data refreshed daily, snapshot 2026-10-23.