How good is GLM-5.2? GLM-5.2 (Max) ranks higher than Claude Opus 4.8 (Thinking) on Code Arena, wher... - 惯性聚合

推荐订阅源

人人都是产品经理

Check Point Blog

大猫的无限游戏

Threat Intelligence Blog | Flashpoint

博客园 - 聂微东

Help Net Security

cs.AI updates on arXiv.org

LINUX DO - 最新话题

博客园 - Franky

阮一峰的网络日志

Hacker News: Front Page

Hacker News: Ask HN

Google DeepMind News

PCI Perspectives

Hacker News - Newest: "LLM"

Schneier on Security

Know Your Adversary

Help Net Security

Simon Willison's Weblog

Java Code Geeks

Visual Studio Blog

CXSECURITY Database RSS Feed - CXSecurity.com

CERT Recently Published Vulnerability Notes

Google Online Security Blog

有赞技术团队

The GitHub Blog

Engineering at Meta

Apple Machine Learning Research

www.infosecurity-magazine.com

About on SuperTechFans

SegmentFault 最新的问题

Hackread – Cybersecurity News, Data Breaches, AI and More

TaoSecurity Blog

WordPress大学

Proofpoint News Feed

Arena.ai(@lmarena_ai)

Check out the full Text and Code Arena: Frontend leaderboards https://t.co/GFZ3FCC7Cl Across the 15 selected categories in the Text Arena, Muse Spark 1.1 improves in 12. The largest inc... Muse Spark 1.1 ranks #9 on Code Arena: Frontend. Highlights: - #2 in the Data & Analytics doma... Muse Spark 1.1 has entered the Code Arena: Frontend at #9! Muse Spark 1.1 reshapes the cost-perform... Arena.ai (@arena) on X Arena.ai (@arena) on X Arena.ai (@arena) on X Test out GPT-5.6 in Battle Mode and Agent Mode at: https://t.co/yZiJuG8ica. Scores incoming. GPT-5.6 Sol, Terra and Luna by @OpenAI are available in the Agent Arena! In Agent Arena, we measure... Arena.ai (@arena) on X Arena.ai (@arena) on X Arena.ai (@arena) on X Arena.ai (@arena) on X Arena.ai (@arena) on X Test out Grok 4.5 in Battle Mode and Agent Mode at: https://t.co/yZiJuG8ica. Scores incoming. Grok 4.5 by @SpaceXAI is now in the Agent Arena! In Agent Arena, we measure models on millions of r... Dig into the Video Arena leaderboard details at: https://t.co/IaLvxeRp5d Meta Muse Video just entered the Video Arena at #3. @AIatMeta’s new video model scored 1459 in the ... In Multi-Image Arena, Meta Muse Image also ranks #2. This is a strong 23 point gap from the next bes... Dig into the Image Arena leaderboard details at: https://t.co/7NVNbVi1Po Exciting news: Meta’s Muse Image just claimed #2 in the Image Arena! Muse Image from @AIatMeta now ... Head over to the Agent Arena leaderboard to dive into the details: https://t.co/5PhJhhhUYI Learn more about the causal tracing methodology for Agent Arena on our blog: https://t.co/bpIkMhEeKL Claude Sonnet 5 (Thinking) by @AnthropicAI debuts at #6 on the new Agent Arena leaderboard. In Agen... source: https://t.co/fz8ZzUSK9k Arena ranked #8 among startups founded since 2020 in web traffic this June, with 34.7M monthly visit... Claude Fable 5 is back - it might be the most impressive model we've ever seen. @petergostev ran it... Now that Fable 5 is back in the Arena, check out this montage of a few of the prompts we put it thro... Now that Fable 5 is back on Arena, watch @petergostev put the re-deployed model by @anthropicAI thro... Test out Claude Fable 5 in Battle Mode and Agent Mode across modalities and contribute your votes. F... See how Claude Fable 5 originally stacked up on the leaderboards at: https://t.co/PjWOaDEXWR The community has been asking how Claude Fable 5 compares before vs. after its latest re-deployment.... Get testing and building with the new Fullstack Code Arena at: https://t.co/DYnDhxb9y7 Code Arena just leveled up with fullstack capabilities 🚀 Introducing the new Fullstack Code Arena.... Code Arena now goes beyond frontend prototypes. Read more about all the new fullstack features in ou... With Fullstack, we now support building more complex apps that require database or backend functiona... Claude Sonnet 5 (Thinking) landed #32 overall for Text. Let's dig into why. In the Text Arena, you ... Claude Sonnet 5 (Thinking) has landed #6 for Code Arena: Frontend. The latest Sonnet scores +29 po... Learn more about Agent Arena’s causal tracing methodology with Evan: https://t.co/e9xKDMXcfC Fable 5 is now in Agent Mode - we’ll see if it holds the lead as new traces come in. https://t.co/8u... Fable 5 is back in the Arena! When it first debuted, Fable 5 ranked #1 in Agent Arena: our benchmar... Check out first impressions of Claude Sonnet 5 in the Agent Arena on YouTube with @petergostev. Sc... See the Video Edit Arena leaderboard details at: https://t.co/d9p8cJDy4K Gemini Omni Flash ranks #2 for Video Edit in the Video Arena! With only seven models ranked for thi... Learn more about the causal tracing methodology for Agent Arena on our blog: https://t.co/7cotZWljYY Test out all the top agentic frontier models in Agent Mode at: https://t.co/8ujN06t7FN Claude Sonnet 5 is ready for you in the Agent Arena! In Agent Arena, we measure models on millions ... Head over to https://t.co/7NVNbVi1Po to dig into the score details. Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) ranks #5 overall for Text-to-Image. It has also lan... Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) has entered the Text-to-Image Arena. It ranks #5 ov... If our mission resonates with you, check out our job openings and reach out: https://t.co/eLzg6u1tYb If you’d like to learn more about the milestone, head over to our blog: https://t.co/shQ4coO5d4 Arena reached a $100M annual revenue run rate just 8 months after launching our evaluation product. ... HappyHorse 1.1 by @HappyHorseATH is in the Video Arena. (Text-to-Video, Image-to-Video & Video Edit)... Head over to the Video Arena at: https://t.co/ozG8iB7Wry Millions of people worldwide bring real-world tasks to Arena - and at that scale, hot/cold storage b... Listen in as our engineering team walks through best practices around how to handle billions of data... More details in Code Arena leaderboard at: https://t.co/15hMCXKs0V Try out Code Arena: Frontend at: https://t.co/DYnDhxb9y7 Learn more about the causal tracing methodology for Agent Arena on our blog: https://t.co/bpIkMhEeKL Head over to the Agent Arena leaderboard to dive into the details. You can also filter by open model... [Token efficiency in Agent Arena] Agent Arena measures agent performance across a range of real-worl... More details and data in the Code Arena: Frontend leaderboard at: https://t.co/15hMCXKs0V

How good is GLM-5.2? GLM-5.2 (Max) ranks higher than Claude Opus 4.8 (Thinking) on Code Arena, wher...

Arena.ai (@a · 2026-06-27 · via Arena.ai(@lmarena_ai)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。