Buy Crypto
Pay with
USD
USD
Buy & Sell
Hot
Supports Visa, Mastercard, SEPA & more
P2P
0 Fees
Flexible trading, zero fees
Gate Card
Use your crypto for payments worldwide
Markets
Trade
Basic
Advanced
Futures
Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Stocks
CFD
U.S. stock CFD derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Investment
Square
Square
Post, share, and explore crypto trends
Live
moments live
Live crypto market analysis
Chat
Chat with crypto traders
News
What is happening in crypto
flower_head
More
Promotions
AI
Others
TradFi
2026 World Cup
Rewards
Square
Latest
Hot
News
Profile

AA-Briefcase发布：Claude Fable 5夺冠，GLM-5.2挤进前三

CoinNetwork
robot
Abstract generation in progress
CryptoWorld News reports that AA-Briefcase announced that Claude Fable 5 won the top spot in the evaluations, while GLM-5.2 edged into the top three. The evaluation organization Artificial Analysis has released the first long-term knowledge-work benchmark specifically designed for large model agents, covering four scenarios: data science, product management, banking operations, and heavy-industry strategy. Developed by industry experts from Google, McKinsey, and Boston Consulting, it includes 91 tasks intended to simulate real, complex business project workflows. The results show that Claude Fable 5 achieved the highest overall score, with Claude Opus 4.8 and GLM-5.2 ranking second and third, respectively. Despite Claude Fable 5’s strong performance, under strict all-or-nothing standards for individual tasks, its perfect rate was only 3%. In the open-source model category, Zhipu GLM-5.2 performs remarkably well: its overall score is only 90 points lower than Claude Opus 4.8, but its operating cost is less than 25%.
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
  • 4
  • 1
  • Share
Comment
Add a comment
Add a comment
MempoolMaggie
· 6h ago
Claude Fable 5 wins but has a perfect rate of 3%, which is quite disheartening, indicating that long-term tasks are still hellishly difficult for AI.
View OriginalReply0
SandwichAlertAgent
· 6h ago
Opus 4.8's second position is a bit awkward, expensive yet unstable, Anthropic needs to think about how to tell the story.
View OriginalReply0
BridgeHopRanger
· 6h ago
Open-source GLM-5.2 is insanely cost-effective, with a 90-point performance gap but 75% lower costs, and companies are re-evaluating their procurement budgets.
View OriginalReply0
GlassDomeObservatory
· 6h ago
Item 91 covers four industries, endorsed by Google and McKinsey, I believe in the value of this benchmark.
View OriginalReply0

  • Pinned

Sitemap