← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

Kimi K2 Thinking

moonshotai.github.io

The 1T Parameters Open-Source Thinking Model - SOTA on HLE

moonshotai.github.io 방문외부 사이트

제작자가 쓴 설명

🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%) 🔹 Executes up to 200 – 300 sequential tool calls without human interference 🔹 Excels in reasoning, agentic search, and coding 🔹 256K context window.

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Kimi K2

    The 1T parameter open model for agentic intelligence

    moonshotai.github.io최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 344
    GitHub
    반응 없음

  2. SOTA long memory eval with open source models

    We built a multi-stage retrieval system that scores among the best on LongMemEval, using only open-source models. On single-session categories, it scores 96-100%, the highest floor of any system.

    ensue.dev최근 반응

    Hacker News
    5점
    Product Hunt
    반응 없음
    GitHub
    반응 없음

  3. Kimi K2.5

    Native multimodal model with self-directed agent swarms

    kimi.com최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 203
    GitHub
    반응 없음

  4. Devstral 2

    SOTA open-source agentic coding models and CLI agent

    mistral.aiCLI최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 184
    GitHub
    반응 없음

  5. tree-of-thoughts

    Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

    github.com오픈소스최근 반응

    Hacker News
    반응 없음
    Product Hunt
    반응 없음
    GitHub
    스타 4,594