Moonshot AI Pushes Kimi K3.1 Pro to Near-Top of AI Rankings

Chinese AI firm Moonshot AI released Kimi K3.1 Pro on October 23, 2026, pushing its latest reasoning model to fourth place on the Artificial Analysis Intelligence Index with a score of 55.

That score trails only Claude Opus 5.5 (58), Claude Sonnet 5.5 (56), and Muse Wonder Full (56) on the index. K3.1 Pro's 55-point result marks an 11-point jump over its predecessor, K3.

Moonshot has scheduled the release of model weights by November 4, 2026. If that timeline holds, K3.1 Pro would become the highest-scoring open-weights model available, cutting the gap between open and proprietary models from 12 points to 3, assuming no other models move. The model is available now through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API. A variant called K3.1 Pro Highspeed, which runs two to three times faster according to the company, is also shipping.

K3.1 Pro's biggest gains show up in agentic tasks. On the GDPval-AA benchmark, it reaches 1,846 Elo per Artificial Analysis, 312 points above K3 and 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 just behind Claude Opus 5.5 (66.4 percent); K3 managed only 13 percent on the same test. Claim-level hallucination rates on Moonshot's internal Kimi Hallu Bench Hard dropped from 23.4 percent with K3 to 8.3 percent, though the company describes this as a stress test rather than a general error rate. GPT-6 Astra records 5.5 percent on the same benchmark. On internal finance benchmarks, K3.1 Pro gained 7.2 points on Financial Modeling and 11.6 points on Financial Research, and Moonshot says it tops all tested models on OfficeQA Pro v2 for general office tasks.

The model also works directly with game engines including Unity, Unreal Engine, and Godot, handling both quick fixes and full project builds, according to Moonshot. On BenchCAD, it scores 92.7 percent with tools, close to Claude Opus 5.5 (96.2 percent) and GPT-6 Astra (95.9 percent), and 72.8 percent without tools, nearly matching Claude Opus 5.5 (73.0 percent). Moonshot says it is strongest at parametric modeling of mechanical parts, architectural models, and configurable products, and 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.

K3.1 Pro keeps the same dimensions as K3, with 2.8 trillion total parameters and 104 billion active ones, plus a one-million-token context window covering both text and images. Artificial Analysis places it at the top of the Pareto frontier, with no model of comparable parameter count scoring 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, nearly identical to K3's $2.00, because the model generates 14 percent more output tokens.

Moonshot devotes part of its technical blog post to cybersecurity, stating that vulnerability research capabilities grew as post-training scaled because cyber content was embedded in the mid-training corpus and related tasks were part of the reinforcement learning 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, while adding that open models also serve defensive purposes like auditing legacy systems. Anthropic has previously shown that even GLM-5.3, which scores 45 on the AA Index, can write exploits at near-Claude Mythos levels.

Moonshot's model weights are due by November 4, 2026, a date that would determine whether K3.1 Pro becomes the top open-weights model on the index.