Moonshot AI K3.1 Pro: Fourth Place on Global Index

Moonshot AI released Kimi K3.1 Pro today, a reasoning model that ranks fourth on the Artificial Analysis Intelligence Index.

The new model scored 55 points. That is an 11 point jump from its predecessor, Kimi K3. It now sits only three points behind the leading proprietary systems.

Moonshot built K3.1 Pro by adding more post training compute to the K3 base. The company says this extra compute drove the performance gains. Artificial Analysis lists Anthropic's Claude Opus 5.5, Claude Sonnet 5.5, and Muse Wonder Full as the only models scoring higher.

The biggest gains appeared in agentic tasks. On the GDPval AA benchmark, K3.1 Pro reached an Elo score of 1,846. That is 312 points higher than K3. It trails Claude Opus 5.5 at 1,866 and Muse Wonder Full at 1,857. On Terminal Bench 4.0, Moonshot reports a score of 65.7 percent. That beats GPT 6 Astra at 58.2 percent but falls slightly short of Claude Opus 5.5 at 66.4 percent. The previous K3 model managed only 13 percent on that test.

The company also reports a drop in hallucinations. On its internal Kimi Hallu Bench Hard, claim level hallucinations fell from 23.4 percent with K3 to 8.3 percent. Moonshot notes that GPT 6 Astra still leads this test at 5.5 percent. On internal finance benchmarks, the model improved by 7.2 points on Financial Modeling and 11.6 points on Financial Research. Moonshot says it tops all tested models on OfficeQA Pro v2.

Coding and 3D modeling capabilities expanded as well. The model works with Unity, Unreal Engine, and Godot. It can write and run scripts for Blender and CAD software without MCP connectors. On the BenchCAD benchmark, K3.1 Pro scores 92.7 percent with tools. That compares to 96.2 percent for Claude Opus 5.5 and 95.9 percent for GPT 6 Astra. Without tools, the score is 72.8 percent, nearly matching Claude Opus 5.5 at 73.0 percent. A new 3D Make feature on Kimi.com allows users to preview, edit, and export 3D models.

The architecture remains the same as K3. It has 2.8 trillion total parameters, with 104 billion active. The context window holds one million tokens. It supports text and images. Artificial Analysis places it on the top of the Pareto frontier for its size. API prices dropped by 33 percent. Input costs are now $2 per million tokens. Output costs are $10 per million tokens. Cache hits cost $0.20 per million tokens. Because the model generates 14 percent more output tokens, the cost per Intelligence Index task is $1.98, nearly identical to the $2.00 cost for K3.

Moonshot addressed cybersecurity in its technical blog. The company says vulnerability research capabilities grew as post training scaled. Cyber related content was part of the general mid training corpus. For the open weights release, the company removed cyber related data from both training phases. On its internal xdev bench hard test, the uncleaned model solved 90.5 percent of tasks. That dropped to 81.0 percent after cleaning. DeepSeek V4.1 Flash scored 85.7 percent, while Kimi K3 scored 33.3 percent.

Moonshot plans to publish the model weights by November 4, 2026. If released as scheduled, K3.1 Pro would become the highest scoring open weights model. That would reduce the gap between open and proprietary models from 12 points to 3 points. Both K3.1 Pro and the faster Highspeed variant are available now through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.