"The company said that the model was trained on 15 trillion mixed visual and text tokens, and that's why it is natively multimodal. It added that the models are good at coding tasks and handling agent swarms - an orchestration where multiple agents work together. In released benchmarks, the model matches the performance of the proprietary peers and even beats them in certain tasks."
"For instance, in the coding benchmark, the Kimi K2.5 outperforms Gemini 3 Pro at the SWE-Bench Verified benchmark, and scores higher than GPT 5.2 and Gemini 3 Pro on the SWE-Bench Multilingual benchmark. In video understanding, it beats GPT 5.2 and Claude Opus 4.5 on VideoMMMU (Video Massive Multi-discipline Multimodal Understanding), a benchmark that measures how a model reasons over videos."
"To let people use these coding capabilities, the company has launched an open-source coding tool called Kimi Code, which would rival Anthropic's Claude Code or Google's Gemini CLI. Developers can use Kimi Code through their terminals or integrate it with development software such as VSCode, Cursor, and Zed. The startup said that developers can use images and videos as input with Kimi Code."
Moonshot AI released Kimi K2.5, an open-source model that understands text, image, and video. The model was trained on 15 trillion mixed visual and text tokens, making it natively multimodal. The models perform strongly on coding tasks and handling agent swarms, where multiple agents coordinate. Benchmarks show parity with proprietary peers and wins on specific tasks. Kimi K2.5 outperforms Gemini 3 Pro on SWE-Bench Verified and scores higher than GPT 5.2 and Gemini 3 Pro on SWE-Bench Multilingual. It also beats GPT 5.2 and Claude Opus 4.5 on VideoMMMU. Moonshot launched Kimi Code, an open-source coding tool that accepts images and videos and integrates with VSCode, Cursor, Zed, and terminals.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]