中国AI型号 Kimi K3.1 Pro正在接近Anthropic的Claude Opus 5.5
关键点
- 中国AI公司Moonshot AI拥有发布 Kimi K3.1 Pro，在人工分析智能指数上以55分跃升至第四位，仅次于Claude Opus 5.5.
- 显示模型在代理任务、编码和3D模型制作方面的主要收益。
- 参数数保持在2.8万亿，但API价格下降了33%。 Moonshot计划在2026年11月前发布模型重量。
Moonshot 电话 AI的新推理模型Kimi K3.1 Pro 获得在人工分析智能指数上排名第四，仅落后于顶级专有模型3分。
中国AI公司Moonshot AI拥有发布 Kimi K3.1 Pro)，是其前身Kimi K3的后训练版本，其后训练计算量明显增加。 模型在人工分析智能指数上得分55分，11分跳过K3，获得位列第四。
根据人工分析，只有Claude Opus 5.5(58),Claude Sonnet 5.5(56),Muse Wonder Full(56)排名较高。 如果到2026年11月4日计划好的Moonshot 发布型号权重，K3.1 Pro将成为可获得的最高评分开放权重模型。 这将缩小开放模型和专有模型之间的差距，从12点缩小到3点，假设届时没有其他变化。
与 K3.1 相邻 Pro,Moonshot正在运输一种叫做K3.1 Pro高速的变体，根据公司的说法，该变体运行速度为2至3倍。 两者现在都通过Kimi.ai,Kimi Work,Kimi代码和Kimi API提供。
代理任务收益最大
K3.1 Pro最强的改进出现在代理任务中。 在GDPval-AA 基准测试上，根据人工分析，它达到1,846 Elo，高于K3的312点。 这使得它仅落后于Claude Opus 5.5(1,866)和Muse Wonder Full(1,857). Moonshot报告为65.7%，领先于GPT-6 Astra(58.2%)，仅次于Claude Opus 5.5(66.4%)。 K3在同一测试中只管理了13%.
幻觉率也急剧下降。 在Moonshot内部的Kimi Halu Bench Hard上，根据公司的说法，索赔层次的幻觉从23.4%的K3下降到8.3%。 Moonshot 称这是压力测试，不是一般误差率的衡量标准。 同一基准测试上的GPT-6 Astra 达到 5.5%，因此仍有边缘。
在内部金融方面基准测试，K3.1 Pro在金融建模方面获得了7.2分，在金融研究方面获得了11.6分。 对于一般的办公任务，模型超过在OfficeQA Pro v2上全部测试了模型，根据Moonshot.
Moonshot的Kimi K3.1 Pro 基准测试表。 所有结果的推理设定为"最大。"
3D 模型和编码
K3.1 Pro直接与Unity,unreal Engine,Godot等游戏引擎合作，根据Moonshot处理快速修复和完整项目建设。 在BeningCAD 基准测试上，它以工具评分92.7%，接近Claude Opus 5.5(96.2%)和GPT-6 Astra(95.9%). 没有工具，它就是达到 72.8%，几乎与Claude Opus 5.5(73.0%)相匹配。
Moonshot 称该模型在机械部件的参数模型，建筑模型，以及可配置产品上最强。 它可以在没有MCP连接器的情况下为Blender和CAD软件编写和运行脚本。 公司还使用发布在Kimi.com上推出一个名为"3D Make"的功能，让用户进行预览，编辑，并导出3D模型。
尺寸相同，价格较低
K3.1 Pro保持与K3相同的尺寸，总参数为2.8万亿，活性参数为1040亿。 上下文窗口跨度为100万令牌，模型既处理文本，也处理图像。 根据人工分析，它坐落在帕雷托边疆的顶端。 没有具有可比参数的模型在情报指数上得分较高。
Token价格下跌33%. 投入费用为每百万令牌2美元(从3美元减少)，产出费用为10美元(从15美元减少)，缓存达到费用为0.20美元(从0.30美元减少)。 每个情报指数任务的费用为1.98美元，几乎与K3(2.00美元)完全相同，因为模型产生的输出符数增加了14%.
网络安全和蓄意限制攻击能力
Moonshot在技术博客文章中，称公司注意到，随着培训后规模的扩大，脆弱性研究能力不断增长，因为与网络相关的内容已嵌入一般的中期培训中，相关任务也是RL环境组合的一部分。
对于开放权重发布，Moonshot从两个培训阶段剥离了网络相关数据。 在其内部的xdev-bench-hard上，它最近复制了Linux内核，Node.js和JavaScriptCore等软件中披露的弱点，不干净的版本解决了90.5%的任务。 数据清理后，K3.1 Pro解决81.0%. DeepSeek-V4.1-Flash在同一测试中达到85.7%，而Kimi K3的得分为33.3%.
Moonshot 称 no 开放权重模型应该推动进攻性网络能力的绝对前沿。 同时，公司希望逐渐提升开放模式所能做的，因为开放模式还服务于审计遗留系统等防御目的。 Anthropic之前显示，即使是在AA指数上评分45的GLM-5.3，也能在近Claude神话水平上写出开发。
AI News Without the Hype – 由人类治愈
订阅THE DECODER免费阅读，每周AI通讯，我们独家的"AI雷达"前沿报告每年6次，全面存档访问，访问我们的评论部分。
现在订阅
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Chinese AI model Kimi K3.1 Pro is closing in on Anthropic's Claude Opus 5.5
Key Points
- Chinese AI company Moonshot AI has released Kimi K3.1 Pro, which jumped to fourth place on the Artificial Analysis Intelligence Index with 55 points, just behind Claude Opus 5.5.
- The model shows major gains in agentic tasks, coding, and 3D modeling.
- The parameter count stays at 2.8 trillion, but API prices drop by 33 percent. Moonshot plans to release the model weights by November 2026.
Moonshot AI's new reasoning model Kimi K3.1 Pro lands at number four on the Artificial Analysis Intelligence Index, just 3 points behind the top proprietary models.
Chinese AI company Moonshot AI has released Kimi K3.1 Pro, a post-trained version of its predecessor Kimi K3 with significantly more post-training compute. The model scores 55 points on the Artificial Analysis Intelligence Index, an 11-point jump over K3 that lands it in fourth place.
Only Claude Opus 5.5 (58), Claude Sonnet 5.5 (56), and Muse Wonder Full (56) rank higher, according to Artificial Analysis. If Moonshot releases the model weights as planned by November 4, 2026, K3.1 Pro would become the highest-scoring open-weights model available. That would shrink the gap between open and proprietary models from 12 to just 3 points, assuming nothing else changes by then.
Alongside K3.1 Pro, Moonshot is shipping a variant called K3.1 Pro Highspeed that runs two to three times faster, according to the company. Both are available now through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Agentic tasks see the biggest gains
K3.1 Pro's strongest improvements show up in agentic tasks. On the GDPval-AA benchmark, it reaches 1,846 Elo according to Artificial Analysis, 312 points above K3. That puts it just behind Claude Opus 5.5 (1,866) and Muse Wonder Full (1,857). On Terminal-Bench 4.0, Moonshot reports 65.7 percent, ahead of GPT-6 Astra (58.2 percent) and barely behind Claude Opus 5.5 (66.4 percent). K3 managed only 13 percent on the same test.
Hallucination rates dropped sharply too. On Moonshot's internal Kimi Hallu Bench Hard, claim-level hallucinations fell from 23.4 percent with K3 to 8.3 percent, according to the company. Moonshot says this is a stress test, not a measure of general error rates. GPT-6 Astra hits 5.5 percent on the same benchmark, so it still has an edge.
On internal finance benchmarks, K3.1 Pro gained 7.2 points on Financial Modeling and 11.6 points on Financial Research. For general office tasks, the model tops all tested models on OfficeQA Pro v2, according to Moonshot.
Moonshot's Kimi K3.1 Pro benchmark table. All results with reasoning effort set to "max."
3D modeling and coding
K3.1 Pro works directly with game engines like Unity, Unreal Engine, and Godot, handling both quick fixes and full project builds, according to Moonshot. On the BenchCAD benchmark, it scores 92.7 percent with tools, close to Claude Opus 5.5 (96.2 percent) and GPT-6 Astra (95.9 percent). Without tools, it hits 72.8 percent, nearly matching Claude Opus 5.5 (73.0 percent).
Moonshot says the model is strongest at parametric modeling of mechanical parts, architectural models, and configurable products. It can write and run scripts for Blender and CAD software without MCP connectors. The company also launched a feature called "3D Make" on Kimi.com that lets users preview, edit, and export 3D models.
Same size, lower prices
K3.1 Pro keeps the same dimensions as K3, with 2.8 trillion total parameters and 104 billion active ones. The context window spans one million tokens, and the model handles both text and images. According to Artificial Analysis, it sits at the top of the Pareto frontier. No model with a comparable parameter count scores higher on the Intelligence Index.
Token prices drop by 33 percent. Input costs $2 per million tokens (down from $3), output costs $10 (down from $15), and cache hits cost $0.20 (down from $0.30). Each Intelligence Index task costs $1.98, almost identical to K3 ($2.00), since the model generates 14 percent more output tokens.
Cybersecurity and deliberate limits on offensive capabilities
Moonshot devotes an entire section of its technical blog post to cybersecurity. The company says it observed that vulnerability research capabilities kept growing as post-training scaled up, because cyber-related content was embedded in the general mid-training corpus and related tasks were part of the RL environment mix.
For the open-weights release, Moonshot stripped cyber-related data from both training phases. On its internal xdev-bench-hard, which reproduces recently disclosed vulnerabilities in software like the Linux kernel, Node.js, and JavaScriptCore, the uncleaned version solves 90.5 percent of tasks. After data cleaning, K3.1 Pro solves 81.0 percent. DeepSeek-V4.1-Flash reaches 85.7 percent on the same test, while Kimi K3 scored 33.3 percent.
Moonshot says no open-weights model should push the absolute frontier of offensive cyber capabilities. At the same time, the company wants to gradually raise what open models can do, since they also serve defensive purposes like auditing legacy systems. Anthropic previously showed that even GLM-5.3, which scores 45 on the AA Index, can write exploits at near-Claude Mythos levels.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now
Auto-fetched and translated by AI Atlas. All rights belong to the original author.