T
traeai
Sign in

公司

lmarena.ai

别名:lmarena_ai

发布Agent Arena相关研究的AI公司

已跟踪 5 条高相关材料

TraeAI 观察

相关材料

已收录 5 条与 lmarena.ai 相关的内容,按评分排序。

New open model: MiniMax M3 by @MiniMax_AI is live in the Arena!

Find it across Text, Vision, Docume...

New Open Model: MiniMax M3 by @MiniMax_AI is Live in the Arena!

lmarena.ai(@lmarena_ai)124 字 (约 1 分钟)
75

MiniMax M3 is the first open-weight model supporting text, vision, document, and code tasks, excelling in benchmarks like SWE-Bench Pro with 1M context length.

入选理由:MiniMax M3 在 SWE-Bench Pro 达到 59.0%,Terminal Bench 2.1 达 66.0%,是当前开源模型中编程能力最强之一。

FeaturedTweet#MiniMax#Open Model#Multimodal#SWE-Bench英文
Asked Gemini 3.5 Flash to render the Petra Treasury. It built the entire stone canyon around it - so...

Gemini 3.5 Flash autonomously constructed the surrounding stone canyon and added ambient sounds when rendering the Petra Treasury, demonstrating agency beyond other frontier models.

入选理由:Gemini 3.5 Flash在渲染任务中自主构建了周围石峡谷,而其他模型未做到这点

FeaturedTweet#Gemini 3.5 Flash#AI generation#lmarena.ai英文
GLM-5.2 (Max) also moves the Pareto Frontier for Code Arena: Frontend.

GLM-5.2 (Max) also moves the Pareto Frontier for Code Arena: Frontend.

lmarena.ai(@lmarena_ai)53 字 (约 1 分钟)
60

GLM-5.2 (Max)在前端代码生成领域取得进展,但信息密度较低,缺乏具体机制和数据支撑。

入选理由:GLM-5.2 (Max)在前端代码生成领域取得进展。

FeaturedTweet#GLM-5.2#前端#AI模型英文

跨材料问答 · lmarena.ai

回答基于:lmarena.ai 相关 5 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.