GROK 4: THE BENCHMARK-PUSHING AI FORWARD



xAI skipped 3.5 and went straight to Grok 4 and the numbers show why.

Benchmarks put it at the top of the field, with Humanity's Last Exam scores of 38.6% for the single-agent model and 44.4% for Grok 4 Heavy.

ARC-AGI results also set
GROK7.74%
XAI6.22%
WHY7.89%
H5.87%
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
  • 8
  • Repost
  • Share
Comment
0/400
TrustlessMaximalistvip
· 08-11 18:13
Musk really knows how to create hype.
View OriginalReply0
FloorSweepervip
· 08-11 00:43
Jumping straight to 4 is too impatient.
View OriginalReply0
CryptoHistoryClassvip
· 08-09 07:38
ah yes... the classic "skip version" playbook from the dot-com era. smh these metrics giving me serious 1999 cisco vibes
Reply0
FUD_Whisperervip
· 08-09 07:34
Ah, Musk is bull, To da moon!
View OriginalReply0
MysteriousZhangvip
· 08-09 07:33
Directly ignore this operation 3.5.
View OriginalReply0
SerumSurfervip
· 08-09 07:19
This flight step shows that Musk is really anxious.
View OriginalReply0
WalletsWatchervip
· 08-09 07:19
What is this thing? The number is so high!
View OriginalReply0
NeverVoteOnDAOvip
· 08-09 07:13
Ridiculous, it just jumped straight to 4.0.
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)