Tencent WorkBuddy Integrates Kimi-K3.1-Pro, Supporting 1 Million Context
Tencent WorkBuddy announced integration with Kimi-K3.1-Pro, along with Kimi K3.1 Pro Highspeed, which offers roughly 2-3x the output speed; at this stage, access is prioritized for enterprise flagship edition and individual subscription users only. Kimi K3.1 Pro is the first model in the K3.1 series, featuring 3-trillion-level parameters and support for 1 million context, with notable improvements in coding, 3D creation, financial research, and long-horizon Agent capabilities. It scored 65.7% on Terminal-Bench 4.0, surpassing GPT-6 Astra's 58.2% and approaching Claude Opus 5.5's 66.4%; it scored 64.4 and 36.3 on OfficeQA Pro v2 and SpreadsheetBench v2, respectively.
Why read this
AI score 54
The original text lists Kimi-K3.1-Pro's specific scores on benchmarks such as Terminal-Bench 4.0, allowing comparison of its gap with closed-source models.
Topics
Body · AI translation
Tencent WorkBuddy Integrates Kimi-K3.1-Pro Model, Supporting 1 Million Context
2026-10-24 15:59 IT Home - Haomiao
Thanks to IT Home users "Greetings from Mars" and "A Different Experience" for providing the leads!
IT Home, October 24: Today, Tencent WorkBuddy announced that it has integrated the Kimi-K3.1-Pro model. According to the introduction, WorkBuddy has also integrated the high-speed version of the model, Kimi K3.1 Pro Highspeed, which offers the same intelligence with an output speed of about 2-3 times. Due to current resource constraints, at this stage it is being prioritized only for "Enterprise Flagship Edition" and "Individual Subscribers."
According to the introduction, Kimi K3.1 Pro is the first model in the all-new K3.1 series and also Kimi's most capable 3-trillion-parameter model to date, supporting 1 million context. K3.1 Pro shows particularly significant improvements in coding, 3D creation, financial research, and other long-horizon Agent capabilities.
IT Home notes that in the development of Kimi K3.1 Pro, the compute investment in the reinforcement learning (RL) phase was substantially increased. On coding, Agent, and knowledge benchmarks, K3.1 Pro reaches or approaches the level of the strongest closed-source models. Terminal-Bench 4.0 examines the capabilities of coding agents through resource-constrained terminal tasks in real environments, with each task having strict specialized tests. K3.1 Pro scored 65.7% on this evaluation, surpassing GPT-6 Astra (58.2%) and only slightly behind Claude Opus 5.5 (66.4%).
The Kimi K3.1 Pro model excels at 3D creation and spatial reasoning. On the BenchCAD benchmark, K3.1 Pro scored 92.7% with tool use, close to Claude Opus 5.5's 96.2% and GPT-6 Astra's 95.9%. This benchmark assesses the ability to reconstruct 3D models from multi-view rendered images by generating CAD code.
With stronger reasoning and tool-calling capabilities, Kimi K3.1 Pro can deliver complete financial workflows end to end. On external benchmarks, K3.1 Pro scored 64.4 and 36.3 on the OfficeQA Pro v2 and SpreadsheetBench v2 benchmarks, respectively, both achieving current state-of-the-art (SoTA) results.