🚨BREAKING: Grok 4 shows strong agent performance on complex coding tasks



⏱ METR reports Grok 4's average time horizon at ~1hr 50min

That's longer than a certain AI company's o3 model (~1hr 30min) on 50% success rate
GROK-6.62%
AGENT-5.64%
post-image
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 5
  • Share
Comment
0/400
DegenMcsleeplessvip
· 08-05 09:30
It seems Musk's new toy is pretty good.
View OriginalReply0
NFT_Therapyvip
· 08-04 20:48
Bull beer is finally not just paper data anymore.
View OriginalReply0
SchrödingersNodevip
· 08-04 20:39
Can you beat Musk?
View OriginalReply0
ContractSurrendervip
· 08-04 20:34
What the heck, it's being praised to the sky again.
View OriginalReply0
OnchainSnipervip
· 08-04 20:28
Again, GPT-4 is being beaten down on the ground.
View OriginalReply0
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate app
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)