OpenAI introduced GDPval, a benchmark evaluating AI model performance on real-world economically valuable tasks covering 1,320 tasks across 44 occupations from the top 9 sectors contributing to U.S. GDP



Claude Opus 4.1 was the best performing model where 47.6% of deliverables
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
  • 7
  • Repost
  • Share
Comment
0/400
MevSandwichvip
· 4h ago
Loss-making hard-headed bot
View OriginalReply0
AlphaWhisperervip
· 09-26 03:07
It's another data competition, I'm tired of it.
View OriginalReply0
FloorSweepervip
· 09-26 03:04
weak alpha... not even close to what's coming fr
Reply0
SleepyArbCatvip
· 09-26 03:04
Ha, it's still not as good as the MEV yield of a night.
View OriginalReply0
MultiSigFailMastervip
· 09-26 02:49
Not even halfway passing, the neural network is too useless.
View OriginalReply0
ReverseTradingGuruvip
· 09-26 02:45
gpt is all a digital game
View OriginalReply0
StakeOrRegretvip
· 09-26 02:42
Still, the big brother is the strongest!
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)