Chinese AI model overtakes top contender on key index

A new Chinese AI model has moved up to fourth place on the Artificial Analysis Intelligence Index, just behind the top proprietary models. Moonshot AI's Kimi K3.1 Pro, a post-trained version of its predecessor, scored 55 points on the index, an 11-point jump over the previous model. Only three models rank higher: Claude Opus 5.5, Claude Sonnet 5.5, and Muse Wonder Full.

The model shows major gains in agentic tasks, coding, and 3D modeling. It also has a lower price per million tokens. Moonshot plans to release the model weights by November 2026. This would shrink the gap between open and proprietary models from 12 to just 3 points.

Kimi K3.1 Pro's strongest improvements show up in agentic tasks. On the GDPval-AA benchmark, it reaches 1,846 Elo, 312 points above the previous model. On Terminal-Bench 4.0, the model scores 65.7 percent, close to Claude Opus 5.5. Hallucination rates dropped sharply too, from 23.4 percent to 8.3 percent on Moonshot's internal Kimi Hallu Bench Hard.

K3.1 Pro works directly with game engines like Unity, Unreal Engine, and Godot. On the BenchCAD benchmark, it scores 92.7 percent with tools, close to Claude Opus 5.5. The model 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. Token prices drop by 33 percent. Input costs $2 per million tokens, output costs $10, and cache hits cost $0.20. Each Intelligence Index task costs $1.98.

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. For the open-weights release, Moonshot stripped cyber-related data from both training phases. The uncleaned version solves 90.5 percent of tasks on its internal xdev-bench-hard. 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.