GROK 4.1 TAKES THE TOP SPOT IN GLOBAL AI RANKINGS With numbers like these, Grok 4.1 makes the leaderboard look under-staffed! Score Checks: • EQ-Bench: 1586, leaving everything else looking underqualified • LM Arena text score: 1483, because Grok 4.1 refuses to play small

分享一个链接

发表一篇文章

任何有趣的，图片，热点新闻，视频，文字...

2601 位用户此时在线

24小时点击排行 Top 10：

哈哈哈，个个都是武林高手啊！

‼️触目惊心！ ‼️六蓝水库崩溃致死17894人！远远超过官方报道数字。当一个国家没有新闻自由言论自由，当权者一定会任意掩盖灾难，而灾难一定会随时发生，且规模难以想象。

印尼政府残酷镇压华人，中共没有一句声明，更没有什么营救措施。最后是美国出动航母以战争威胁印尼政府，政府下令制止暴动的，所以全世界华人感激美国，那句宁为美国狗就是这时候发出的！

8月10日晚上8点，海南文昌卫星发射中心。一枚携带多枚卫星的长征七号火箭在发射约 85 秒后爆炸。

When they say China is cheap, it really is.

8月9日，受台风“白海豚”影响，浙江温州遭遇强风雨天气。停靠在温州瓯江上的“明珠七号”船舶发生沉没。

Anyone want to look at her engine?

8月9日，上海遭遇强降雨，多地出现严重积水。网传现场视频显示，徐汇区武康路一带道路大面积被淹，路面几乎形成“水道”，汽车和电动车只能涉水通行，部分路段积水已没过车辆轮胎相当一部分。视频开头还可见大量雨水不断向下沉空间倾泻，沿街商铺、人行区域也被积水覆盖。

身穿“救护救生”服，专治不服 8月10日，青岛石老人海水浴场，一名男子被多名穿着“救护、救生”衣服的人围起来打，按在地上拳打脚踢，不仅攻击头部，甚至用脚猛踹其下体。

8月1日，一名研究生应届毕业生发视频称，她今年5月10日与一所民办高中签订教师劳动合同，并为此拒绝了其他学校的offer。合同约定8月1日入职，她当天正在家中收拾行李准备报到，却突然接到学校人事通知，称“今年招到的学生比较少，不需要这么多老师了”，无法再提供教师岗位。

8月9日晚，徐州乐园欢乐世界特技表演期间，一名演员在表演“火裙舞”时发生意外，裙摆被引燃，现场缺乏紧急处置预案，第一时间无法扑灭燃烧的衣服，导致演员被烧伤。

摄影师慕名而来给烤斯克拍了一组照片，还真有那味儿了。🫪

漫展烧姬coser

成都一市民在建行购金条被检出为铜警方介入调查 8月9日，四川成都，一名网友反映，其在建设银行购买的金条，送往黄金店进行加工时，被发现材质实为铜。当事人当场报警，目前警方已介入处理。

投稿，8月9号晚上武汉一天桥一名城管进行暴力执法拿器械持续殴打摊贩头部，目前为首的平安武汉抖音账号评论区已被大量网友爆破，预计8月10号早上8点左右视频将会全部下架 👤 来自: 秋

这斧子放在古代战场就太凶残了

感谢纽约人民替旺旺发声！曝光五个小恶魔！

Watch video

8月10日下午，浙江嘉善县施家北路与环北东路交叉口附近，一栋建筑突发起火。现场火势猛烈，受风力影响，火焰不断向上蹿升，一度高达数十米。现场有人员发生昏迷被救护车拉走。

Watch video

毛泽东毛腊肉的尸体被烧了吗？

是不是体内封印了4年的大白之魂又觉醒了

She thinks she isn't being seen.🥰🥰

很多人可能不知道：中共当年大力宣传雷锋事迹，核心目的并非单纯表彰他做了多少好事，而是借此推广《毛泽东选集》。雷锋本质上是一个被精心打造的“工具人”。

“体重不足百斤的女孩，能扛起85公斤的老人” 8月10日，浙江日报报道，浙江省宁波市象山县花墙村村支书在台风天气中坚守两天两夜。她在接受媒体采访时表示，自己99斤的体重现在能扛起85公斤的老人。报道发出后引发网友质疑，许多评论区随后被清空。

本站自动实时分享网络热点
24小时实时更新
所有言论不代表本站态度
欢迎对信息踊跃评论评分
评分越高，信息越新，排列越靠前

2

1

0

GROK 4.1 TAKES THE TOP SPOT IN GLOBAL AI RANKINGS
With numbers like these, Grok 4.1 makes the leaderboard look under-staffed!
Score Checks:
• EQ-Bench: 1586, leaving everything else looking underqualified
• LM Arena text score: 1483, because Grok 4.1 refuses to play small
btc
( twitter.com )

8个月前由 Mario Nawfal 提交

GROK 4.1 TAKES THE TOP SPOT IN GLOBAL AI RANKINGS

With numbers like these, Grok 4.1 makes the leaderboard look under-staffed!

Score Checks:

• EQ-Bench: 1586, leaving everything else looking underqualified

• LM Arena text score: 1483, because Grok 4.1 refuses to play small

• 64.78 percent win rate over Grok 4.0 in straight matchups

• Accuracy and nuance upgraded like it was overdue

No surprise that Grok 4.1 now sits where every other model wanted to be!

Source: @CodeByPoonam

1周内 1个月内 1年内全部时间

1
2
3
4
5
6
...
400
下一页

1

2

1

1

Yep, Grok 4 officially takes the gold! 🥇
Always the new champion, always on top
Grok won the gold medal in the IMO 🏆
btc
( twitter.com)

1年前 • X Freeze 0 评论

2

2

1

1

Here are the key improvements in Grok 4.1 as compared to its previous models:
▸ Better user preference: In blind pairwise tests during rollout, Grok 4.1 was preferred ~64.78% of the time over the previous production model.
▸ Enhanced emotional and interpersonal ability: It
btc
( twitter.com)

8个月前 • DogeDesigner 0 评论

3

2

1

1

Grok 4.1 Fast just dropped on the API 🔥
Until Dec 3rd:
✦ Grok 4.1 Fast = FREE on OpenRouter
✦All Agent Tools = 100 % FREE
This is the agent model we've all been waiting for:
✦ Tool calling: #1 on Berkeley leaderboard
✦ Real-world: 100% on τ²-bench Telecom
✦ Context: 2M
btc
( twitter.com)

8个月前 • TΞTSUØ • 下载视频 0 评论

00:00:14

4

2

1

1

Grok 4.1 is also much better at writing.
On Creative Writing v3, Grok 4.1 scores 1722 Elo, a remarkable 600-point gain over our previous model.
btc
( twitter.com)

8个月前 • xAI 0 评论

5

2

1

1

4.1 is actually a major release of Grok
btc
( twitter.com)

8个月前 • Elon Musk 0 评论

6

2

1

1

🚨GROK TAKES TOP 1 SPOT—LEAVES CHATGPT BEHIND
Elon:
“Grok is number 1 and continues to improve. The results are based on a version of Grok that is 2 weeks old. Significant improvements since then.”
These rankings are based on blind human evaluations, proving Grok-3 is the real
btc
( twitter.com)

1年前 • Mario Nawfal 0 评论

7

2

1

1

xAI just released Grok 4.1 Fast API
Ranks #1 on 𝜏²-Bench on Telecom (Agentic Tool Use) - Outperforms Gemini 3 Pro
- State-of-the-art tool calling
- Massive 2M Context Window
- Trained for the real world use
Grok 4 Fast non-reasoning ➝ Instant Response
Grok 4 Fast - Reasoning
btc
( twitter.com)

8个月前 • X Freeze 0 评论

8

2

1

1

Introducing Grok 4.1, a frontier model that sets a new standard for conversational intelligence, emotional understanding, and real-world helpfulness.
Grok 4.1 is available for free on and our mobile apps.

btc
( twitter.com)

8个月前 • xAI 0 评论

9

2

1

1

Many updates and fixes have been applied to Grok 4.1 and many more to come!
Going forward, Grok 4.1 will spend more compute time thinking about your question to improve accuracy.
btc
( twitter.com)

8个月前 • Elon Musk 0 评论

10

2

1

1

Grok 4.1 Fast just made a nearly 3X jump in long-context accuracy
A key challenge for AI models is that as chats get longer, most AIs forget. They lose the thread, make stuff up, or drop instructions.
Grok 4.1 Fast fixes this. And it’s a huge deal.
It was specifically trained
btc
( twitter.com)

8个月前 • X Freeze 0 评论

11

2

1

1

Grok 4.1 Fast with reasoning just beat Gemini 3!
btc
( twitter.com)

8个月前 • Elon Musk 0 评论

12

2

1

1

ask yourself which AI you want teaching your kids
Grok 4.1 vs gpt 5.1 on “is Trump fascist”
Notice the implications in each answer
btc
( twitter.com)

8个月前 • Arthur MacWaters 0 评论

13

2

1

1

Grok 4.1 just broke the Text Arena leaderboard, hitting a massive record-breaking 1483 score AND claiming both #1 and #2 spots
This is officially the highest ranking ever...
btc
( twitter.com)

8个月前 • X Freeze 0 评论

14

2

1

1

Grok 4.1 holds both first and second place on LMArena
btc
( twitter.com)

8个月前 • Elon Musk 0 评论

15

2

1

1

Grok 4.1 Thinking also Ranks #1 in Arena Expert Leaderboard
btc
( twitter.com)

8个月前 • Tech Dev Notes 0 评论

16

2

1

1

BREAKING 🚨 Grok 4 Fast claims rank no. 1 today on OpenRouter crossing Grok Code Fast.
xAI is its own competition and continues to dominate the leaderboard with top 2 positions consistently by a huge margin.
Imagine what happens when Grok 4.1 releases soon.
btc
( twitter.com)

10个月前 • Prashant 0 评论

17

2

1

1

LLMs acing math olympiads? Cute.
But BALROG is where agents fight dragons (and actual Balrogs)🐉😈
And today, Grok-4 ( takes the gold 🥇
Welcome to the podium, champion!
btc
( twitter.com)

1年前 • Davide Paglieri 0 评论

18

2

1

1

The link below any Grok Imagine video now takes you to that video with the prompt used to create it, so that you can easily learn how create a similar scene
btc
( twitter.com)

9个月前 • Elon Musk • 下载视频 0 评论

00:00:05

19

2

1

1

So xAI just released grok 4.1 and it's the best model ever created. Both in metrics and vibes. Gemini 3 is coming next.
What will happen to the OpenAI brand when they are constantly behind?
btc
( twitter.com)

8个月前 • Yaroslav 0 评论

20

2

1

1

A knight who takes his fish for a walk
Grok Imagine
btc
( twitter.com)

1年前 • Knight World • 下载视频 0 评论

00:00:06

21

2

1

1

Grok 4.1 just released.
You should notice a significant increase in speed and quality.
btc
( twitter.com)

8个月前 • Elon Musk 0 评论

22

2

1

1

Grok 4.1 has higher emotional intelligence, empathy, and interpersonal skills, scoring 1586 on EQ-Bench.
btc
( twitter.com)

8个月前 • xAI 0 评论

23

2

1

1

Grok 4.1 first impressions:
* Very different writing style, much more personal.
* Much improved image understanding, sees even small details.
* Comes in two flavors, normal and "thinking".
* Quite fast, even the thinking version.
btc
( twitter.com)

8个月前 • Mark Kretschmann 0 评论

24

2

1

1

Grok 4.1 is based
#1 on LMArena, high IQ + high EQ, exceptionally fast, state-of-the-art capability, empathetic & perceptive, creative writing, minimal hallucinations and ultra-reliable.
Did you try it?
btc
( twitter.com)

8个月前 • Dogan Ural 0 评论

1
2
3
4
5
6
...
400
下一页