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
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
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
Promotions
AI
Gate AI
Your all-in-one conversational AI partner
Gate AI Bot
Use Gate AI directly in your social App
GateClaw
Gate Blue Lobster, ready to go
Gate for AI Agent
AI infrastructure, Gate MCP, Skills, and CLI
Gate Skills Hub
10K+ Skills
From office tasks to trading, the all-in-one skill hub makes AI even more useful.
GateRouter
Smartly choose from 40+ AI models, with 0% extra fees
SOOHAK Benchmark Reveals AI Model Flaws: Ability to Identify Unsolvable Math Problems Does Not Exceed 50%
AIMPACT News, May 17 (UTC+8), a new AI math benchmark test SOOHAK created by the 64-bit mathematician alliance reveals critical flaws in AI models. The test includes 439 handwritten tasks, of which 99 are deliberately designed to be unsolvable. Google Gemini 3 Pro leads in research-level problems, achieving 30% accuracy, but no model can identify unsolvable tasks with over 50% accuracy. Research shows that more computational resources can improve a model’s problem-solving ability but cannot enhance its ability to recognize unsolvable problems. SOOHAK aims to quantify the gap between AI’s few standout achievements and the widespread research skills still lacking in the system.