Grok 4 is still state-of-the-art on ARC-AGI-2 among frontier models.15.9% for Grok 4 vs 9.9% for GPT-5.

发布时间: 2025-08-08 02:47:12

1分

数据加载中

关注推特

收听电报

2

1

0

Grok 4 is still state-of-the-art on ARC-AGI-2 among frontier models.
15.9% for Grok 4 vs 9.9% for GPT-5.
btc
( twitter.com )

3小时前由 François Chollet 提交

点击图片查看原图

Markdown支持

评论加载中...

您可能感兴趣的：更多

1

2

1

1

GROK 4 MAKES GPT AND GEMINI LOOK OLD
Elon dropped Grok 4, and it’s basically an AI on steroids.
It's faster, smarter, and now it even understands images.
While GPT and Gemini still play with old data, Grok 4 is plugged into X for live updates, so it actually knows what’s
btc
( twitter.com)

27天前 • Mario Nawfal • -- 点击 0 评论

2

2

1

1

Grok 3 feels like talking with an adult. Claude is still lobotimized.
btc
( twitter.com)

5个月前 • Tom Blomfield • -- 点击 0 评论

3

2

1

1

Btw, Grok 2 is still being used to explain 𝕏 posts. That will update to Grok 3 in a day or two.
btc
( twitter.com)

5个月前 • Elon Musk • -- 点击 0 评论

4

2

1

1

Just imagine a 2012 Model S getting Grok 4. 13 years later, it will still be the most intelligent vehicle out there in the world. This is going to be happening by latest next week.
btc
( twitter.com)

27天前 • Teslaconomics • -- 点击 • 下载视频 0 评论

00:01:12

5

2

1

1

Grok voice early beta is now available on the app.
This is early beta, so expect issues (that will be resolved fast), but it’s still awesome.
btc
( twitter.com)

5个月前 • Elon Musk • -- 点击 0 评论

6

2

1

1

I'm hearing people say "Grok 4 is slow".
Grok 4 V.s. GPT o3.
Grok 4: Thought for 14 seconds.
GPT o3: Thought for 1 min 6 seconds.
Grok 4 was faster and produced superior code.
btc
( twitter.com)

11天前 • Tetsuo • -- 点击 • 下载视频 0 评论

00:01:50

7

2

1

1

Joe Rogan agrees with Elon Musk, the only artificial intelligence that can be trusted is Grok
Elon Musk “Grok is aspirationally a maximally truth-seeking ai, even if that truth is like politically incorrect”
Other AI like Google Gemini secretly still contain DEI, “The sort of
btc
( twitter.com)

4个月前 • Wall Street Apes • -- 点击 • 下载视频 0 评论

00:07:12

8

2

1

1

Grok 4 is smart. Tested a block sparse attention problem which both o3 and Claude opus failed. Grok 4 knows it.
btc
( twitter.com)

27天前 • Bing Xu • -- 点击 0 评论

9

2

1

1

🚨🇺🇸GROK 3 IS AMERICA’S ANSWER TO DEEPSEEK—AND IT’S DOMINATING
xAI deserves credit for building world-class reasoning models at record speed—proving that America still leads in AI.
With Grok 3 outperforming competitors, it’s clear xAI is setting the new standard for
btc
( twitter.com)

5个月前 • Mario Nawfal • -- 点击 0 评论

0.03773 Second , Gzip Enable.本网所有言论均来自网络，不代表本网站立场。联系方式: [email protected]

©2012.11.21 bad.news All rights reserved. 社区自动运营第 -- 年零 -- 天
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

关注推特