Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight...
Kimi.ai@Kimi_Moonshot
18 views
Oct 24, 2026
~1 min read
Advertisement
1
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1…
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1…
2
On Terminal-Bench 4.0, which evaluates coding agents on realistic, resource-constrained terminal tasks using strict task-specific tests, K3.1 Pro scores 65.7%, ahead of GPT-6 Astra (58.2%) and narrowly behind Claude Opus 5.5 (66.4%).
3
K3.1 Pro works directly in the tools used by the 3D modeling and game industries - Blender, Unreal Engine, Godot, and CAD.
On BenchCAD, which tests 3D reconstruction from multi-view renderings through CAD code generation, it scores 92.7% with tools, approaching Claude Opus 5.5 (96.2%) and GPT-6 Astra (95.9%).
K3.1 Pro can deliver a fairly complete project, from asset construction to scene assembly, animation, and rendering.
On BenchCAD, which tests 3D reconstruction from multi-view renderings through CAD code generation, it scores 92.7% with tools, approaching Claude Opus 5.5 (96.2%) and GPT-6 Astra (95.9%).
K3.1 Pro can deliver a fairly complete project, from asset construction to scene assembly, animation, and rendering.
0:19
4
K3.1 Pro is SOTA on OfficeQA Pro v2 (64.4). On internal benchmarks, it improves over K3 by 7.2 points on financial modeling and 11.6 points on financial research, and scores ~4.2× K3 on simulated business operation.
Example outputs: an NVDA DCF/LBO model with fully linked statements and traceable formulas, a CATL investment-committee deck, and a quantum-computing sector report with source-level citations.
Example outputs: an NVDA DCF/LBO model with fully linked statements and traceable formulas, a CATL investment-committee deck, and a quantum-computing sector report with source-level citations.
5
K3.1 Pro API and K3.1 Pro Highspeed (2-3× faster), both available now at platform.kimi.ai.
6
Full tech blog at:
kimi.ai/blog/kimi-k3-1…
kimi.ai/blog/kimi-k3-1…
