Kimi K3.1 Pro ships with 1M context and open weights due Nov 4
Source
kimi.ai
Author
Kimi_Moonshot
Date
Why it matters
Kimi K3.1 Pro (1M context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →) is available now via API at $2/$10 per MTok, with open weights due by Nov 4. Moonshot reports 65.7% on Terminal-Bench 4.0, near Claude Opus 5.5, and describes removing cyber data from training to limit offensive capability.
Key takeaways · AI-distilled
Moonshot says K3.1 Pro is Kimi K3 with substantially more post-training compute and joint RL across hundreds of domains. It reports 65.7% on Terminal-Bench 4.0 with the Claude Code harness, versus 58.2% for GPT-6 Astra and 66.4% for Claude Opus 5.5.
In an internal test, K3.1 Pro built a human walking simulator, refining the controller over 167 missions and 420 reviews until the simulated human walked for 11.2 seconds instead of collapsing. When reward shaping stalled on arm motion, it found and fixed 36 moment-arm errors.
On Moonshot's internal Kimi Hallu Bench Hard, the claim-level hallucinationWhen a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.Full definition → rate fell from 23.4% for K3 to 8.3%. Moonshot cautions the set is a deliberately adversarial stress test, so these rates do not represent everyday error rates.
Moonshot traced rising vulnerability-research agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → to cyber content inside its general mid-training corpus and RL environments, and removed that data from both stages for the open-weight release while keeping the general coding tasks.
On Moonshot's in-house xdev-bench-hard, a checkpoint without that data removal solved 90.5% of exploit tasks at pass@3 versus 81.0% for the released model. Moonshot says K3.1 Pro's cyber capability still trails frontier proprietary models public for at least three months.
Terms in this piece · Glossary
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
