We tested top foundation models on the International Olympiad in Informatics (IOI) - a programming competition that tests algorithmic thinking and C++ coding skills. We found 4 to be the clear SOTA winner, scoring first place on both 2024 and 2025 exams. 🥇📊👏

发布时间: 2025-08-12 18:31:42

1分

数据加载中

关注推特

收听电报

We tested top foundation models on the International Olympiad in Informatics (IOI) - a programming competition that tests algorithmic thinking and C++ coding skills. We found 4 to be the clear SOTA winner, scoring first place on both 2024 and 2025 exams. 🥇📊👏
btc
( twitter.com )

3小时前由 Vals AI 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

In the latest Box AI Enterprise Evaluation, we tested Grok 4. We have seen how this new model moves beyond surface-level retrieval to tackle sophisticated business logic, perform precise calculations, make inferences based on qualitative patterns, and pinpoint critical
btc
( twitter.com)

29天前 • Box • -- 点击 • 下载视频 0 评论

00:02:29

In Guangdong province, people tested positive for Chikungunya virus are forced to be quarantined in mosquito nets.
It is the same BS we saw with COVID. Why not quarantine the mosquitoes instead?
时政
( twitter.com)

昨天 • The Great Translation Movement 大翻译运动 • -- 点击 • 下载视频 0 评论

00:00:13

On January 15th, an American netizen posted on Xiaohongshu: "I'm also interested in Marxism, but I've always been confused. Once we revolt, what do we do next? How do we proceed? How do we establish a stable government so that greedy people won't climb to the top and exploit
时政
( twitter.com)

6个月前 • The Great Translation Movement 大翻译运动 • -- 点击 0 评论

I’m currently getting legal advice from a top Barrister and constitutional lawyer about suing the police for wrongful arrest. Seems we might have a case.
时政
( twitter.com)

1个月前 • Brendan Kavanagh (Dr K) • -- 点击 0 评论

The chair has been tested and approved
有趣
( twitter.com)

5个月前 • Virality Clips • -- 点击 • 下载视频 0 评论

00:00:27

The chair has been tested and approved
有趣
( twitter.com)

1个月前 • NO CONTEXT HUMANS • -- 点击 • 下载视频 0 评论

00:00:27

Announcing Artificial Analysis State of AI: China 🇨🇳
For the first time, we are charting the rise of China’s top AI companies to the AI frontier. In this benchmarking report, we map the Chinese AI ecosystem and present comparisons to leading US models.
DeepSeek R1 didn’t
时政
( twitter.com)

6个月前 • Artificial Analysis • -- 点击 0 评论

We have sent 2 dangerous top MS-13 leaders plus 21 of its most wanted back to face justice in El Salvador. Also, as promised by we sent over 250 alien enemy members of Tren de Aragua which El Salvador has agreed to hold in their very good jails at a fair price that will
btc
( twitter.com)

4个月前 • Secretary Marco Rubio • -- 点击 0 评论

The fable of the rabbit and the tortoise has been tested in real life. 😂
有趣
( twitter.com)

10个月前 • Figen • -- 点击 • 下载视频 0 评论

00:00:38

We tested top foundation models on the International Olympiad in Informatics (IOI) - a programming competition that tests algorithmic thinking and C++ coding skills. We found 4 to be the clear SOTA winner, scoring first place on both 2024 and 2025 exams. 🥇📊👏 btc ( twitter.com )

btc

In the latest Box AI Enterprise Evaluation, we tested Grok 4. We have seen how this new model moves beyond surface-level retrieval to tackle sophisticated business logic, perform precise calculations, make inferences based on qualitative patterns, and pinpoint critical btc ( twitter.com)

btc

In Guangdong province, people tested positive for Chikungunya virus are forced to be quarantined in mosquito nets. It is the same BS we saw with COVID. Why not quarantine the mosquitoes instead? 时政 ( twitter.com)

时政

On January 15th, an American netizen posted on Xiaohongshu: "I'm also interested in Marxism, but I've always been confused. Once we revolt, what do we do next? How do we proceed? How do we establish a stable government so that greedy people won't climb to the top and exploit 时政 ( twitter.com)

时政

I’m currently getting legal advice from a top Barrister and constitutional lawyer about suing the police for wrongful arrest. Seems we might have a case. 时政 ( twitter.com)

时政

The chair has been tested and approved 有趣 ( twitter.com)

有趣

The chair has been tested and approved 有趣 ( twitter.com)

有趣

时政

We have sent 2 dangerous top MS-13 leaders plus 21 of its most wanted back to face justice in El Salvador. Also, as promised by we sent over 250 alien enemy members of Tren de Aragua which El Salvador has agreed to hold in their very good jails at a fair price that will btc ( twitter.com)

btc

The fable of the rabbit and the tortoise has been tested in real life. 😂 有趣 ( twitter.com)

有趣

创建一个新帐户

登录

We tested top foundation models on the International Olympiad in Informatics (IOI) - a programming competition that tests algorithmic thinking and C++ coding skills. We found 4 to be the clear SOTA winner, scoring first place on both 2024 and 2025 exams. 🥇📊👏
btc
( twitter.com )

In the latest Box AI Enterprise Evaluation, we tested Grok 4. We have seen how this new model moves beyond surface-level retrieval to tackle sophisticated business logic, perform precise calculations, make inferences based on qualitative patterns, and pinpoint critical
btc
( twitter.com)

In Guangdong province, people tested positive for Chikungunya virus are forced to be quarantined in mosquito nets.
It is the same BS we saw with COVID. Why not quarantine the mosquitoes instead?
时政
( twitter.com)

On January 15th, an American netizen posted on Xiaohongshu: "I'm also interested in Marxism, but I've always been confused. Once we revolt, what do we do next? How do we proceed? How do we establish a stable government so that greedy people won't climb to the top and exploit
时政
( twitter.com)

I’m currently getting legal advice from a top Barrister and constitutional lawyer about suing the police for wrongful arrest. Seems we might have a case.
时政
( twitter.com)

The chair has been tested and approved
有趣
( twitter.com)

The chair has been tested and approved
有趣
( twitter.com)

We have sent 2 dangerous top MS-13 leaders plus 21 of its most wanted back to face justice in El Salvador. Also, as promised by we sent over 250 alien enemy members of Tren de Aragua which El Salvador has agreed to hold in their very good jails at a fair price that will
btc
( twitter.com)

The fable of the rabbit and the tortoise has been tested in real life. 😂
有趣
( twitter.com)