lmarena.ai(@lmarena_ai)
Kimi K2.6 by @Kimi_Moonshot is now live on Arena. Evaluate it in Battle Mode across Text, Vision, C...
7.2内容质量
TL;DR · AI 摘要
Kimi K2.6上线Arena平台，支持多模态评测，涵盖文本、视觉、代码等场景，开源模型在多个基准测试中表现优异。
核心要点
- Kimi K2.6在HLE、SWE-Bench等编码基准测试中达到当前开源SOTA水平。
- 新增长程编码能力，支持4000+ token上下文的复杂任务处理。
- 支持Battle Mode多维度横向评测，包括图像转Web开发和文档理解等新场景。
#Kimi#大模型#开源#代码生成
打开原文Evaluate it in Battle Mode across Text, Vision, Code, Image-to-WebDev, and Document Arena!
Scores incoming - start prompting and get voting. https://t.co/SZVN4R3eGu" / X
Kimi K2.6 by
is now live on Arena. Evaluate it in Battle Mode across Text, Vision, Code, Image-to-WebDev, and Document Arena! Scores incoming - start prompting and get voting.
Quote
Kimi.ai
@Kimi_Moonshot
12h
Meet Kimi K2.6: Advancing Open-Source Coding 
Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: Long-horizon coding - 4,000+
