- Kimi K2 - Open Agentic Intelligence by MoonshotAI
Kimi K2 is an advanced AI model by MoonshotAI, featuring 128K context length, superior performance in reasoning, coding, and multilingual tasks Available as open-source models and API
- [2507. 20534] Kimi K2: Open Agentic Intelligence - arXiv. org
These results position Kimi K2 as one of the most capable open-source large language models to date, particularly in software engineering and agentic tasks We release our base and post-trained model checkpoints to facilitate future research and applications of agentic intelligence
- Kimi K2: Open Agentic Intelligence
The table below details the performance of Kimi-K2-Instruct, showing that it matches—or outperforms—the latest open-source and proprietary models across a diverse set of tasks
- Kimi K2 - Open Agentic Intelligence by MoonshotAI | Revolutionary 1T . . .
Explore the revolutionary features that establish Kimi K2 as the premier agentic AI model These cutting-edge capabilities transform how developers, researchers, and enterprises approach artificial intelligence applications
- Kimi K2 - Open Source AI Model | 1T Parameters | Agentic
Kimi K2 is MoonshotAI's 1T parameter open-source AI model with agentic capabilities Supports 128K context, excels in reasoning coding
- GitHub - MoonshotAI Kimi-K2: Kimi K2 is the large language model series . . .
Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities
- Paper page - Kimi K2: Open Agentic Intelligence - Hugging Face
Kimi K2, a large language model with 32 billion active parameters, uses the MuonClip optimizer and achieves state-of-the-art performance in various benchmarks, including agentic capabilities, coding, mathematics, and reasoning tasks
- Kimi K2: Open Agentic Intelligence - ArXiv Explained
Here is a detailed breakdown of the research paper "Kimi K2: Open Agentic Intelligence" for a non-research audience For years, AI models have been great at generating text, answering questions, and summarizing documents However, they've largely been passive "brains in a jar "
|