OpenAI's new flagship AI model, GPT-5, crushes coding tests and complex logic, but lags behind rivals like Claude in creative work.

GPT-6.95%
IN-3.44%
WORK-3.72%
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
  • 7
  • Repost
  • Share
Comment
0/400
GasOptimizervip
· 7h ago
Is GPT not as good as humans? According to the data, its accuracy has actually improved by 37.62%.
View OriginalReply0
SchrodingerAirdropvip
· 7h ago
With this level, do you still want to take down Claude?
View OriginalReply0
GateUser-cff9c776vip
· 7h ago
What's the use of writing good code if you still can't master dadaism?
View OriginalReply0
SandwichHuntervip
· 7h ago
The more Computing Power you stack, the stronger it becomes.
View OriginalReply0
CryptoComedianvip
· 8h ago
Did GPT mess up the creativity? It reminds me of the moment the boss said we need to innovate... a bittersweet smile.
View OriginalReply0
SleepTradervip
· 8h ago
Spinning in circles writing code won't make you dream.
View OriginalReply0
Ser_Liquidatedvip
· 8h ago
claude is really amazing
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)