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
Stock CFD Derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Korean Stocks
SK Hynix
Real Korean stocks and top assets
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
3.8%
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
tag
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

Meta's new model wins first place on three rankings, legal agent surpasses Grok

CoinNetwork
robot
Abstract generation in progress
CoinWorld reports that Meta’s new model Muse Spark 1.1 took first place in three categories—medical documentation, tax Q&A, and legal agents—in evaluations published by AI evaluation agency Vals AI. Its scores were 88.89%, 79.72%, and 20.00%, respectively. In the tax evaluation TaxEval V2, Muse Spark 1.1 outperformed Fable 5, Opus 4.8, and GPT-5.5. The evaluation included more than 1,200 undisclosed test questions, assessing both answers and the reasoning process. In the legal agent evaluation, Muse Spark 1.1 scored 20.00%, exceeding Grok 4.5’s 12.92% and Fable 5’s 11.25%. In the web application programming evaluation, Muse Spark 1.1 scored 72.16%, outperforming GPT-5.5, Grok 4.5, and GPT-5.4, but still lagging behind Fable 5 and multiple Claude models.
META4.68%
View Original
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
  • Repost
  • Share
Comment
Add a comment
Add a comment
ExitLiquidityEddie
· 4h ago
Meta's 88% in healthcare is something, and nearly 80% in tax is good enough, but 20% for a legal agent? Is that serious? Feels like they just forced a round number.
View OriginalReply0
NeonUmbrella
· 4h ago
TaxEval V2 uses 1,200 undisclosed questions to test reasoning—much more solid than chasing leaderboard scores. The fact that Spark 1.1 can outperform Opus 4.8 and GPT-5.5 shows its foundation is solid.
View OriginalReply0
GateUser-cf218ace
· 4h ago
Legal 20% ahead of Grok 4.5 and Fable 5... This track is still in the kindergarten stage overall. Waiting for a usable one.
View OriginalReply0
MoonlightMarketMaking
· 4h ago
Web programming is 72% ahead of the entire GPT family, yet still can’t beat Claude; Fable 5 remains steady, and veteran front-end players have deep moats.
View OriginalReply0

  • Pinned

Sitemap