DeepNewz, mobile.

People-sourced. AI-powered. Unbiased News.

Screenshot of DeepNewz app showing story detail view.

Screenshot of DeepNewz app showing story list view.

Search

For You

Agentic Evaluations News

Footer

AI

AI Fundraising
AI Modeling
AI Products

Business

Automobile
Company Earnings
Economics
Law
Prediction Markets
Real Estate
Rumors
Stocks
VC

Crypto

Airdrops
Blockchains
CBDCs
DeFi
Hacks
Markets
Memecoin
Mining
NFT
Regulation

Culture

Anime
Celebrities
Crime
Education
Movies
Music
Obituary
TV
Video Games

Environment

Climate
Energy
Natural Disasters
Natural Resources
Sustainability

Politics

DOGE
Epstein Files
Executive Orders
Tariffs
US Domestic Policy
US Elections
US Foreign Policy
US Gov Appointments
US Judiciary
US Legislation
War

Science

Archeology
Bio
Health
Math
Pharma
Physics
Space

Sports

Boxing
Chess
Cricket
Golf
Hockey
MLB
NBA
NCAA
NFL
Olympics
PGA
Poker
Racing
Rugby
Soccer
Tennis
UFC

Tech

AR-VR
Fintech
Infosec
IoT
Metaverse
Policy
Robotics
Smart Home
Software
Startups
Wearables

United States

Arizona
Boston
California
Chicago
Colorado
Detroit
Florida
Georgia
Las Vegas
Los Angeles
New Jersey
New Mexico
New York
Ohio
Oregon
Philadelphia
San Francisco
Seattle
Texas
Utah
Washington DC

World

Terms of Service

WhatsApp YouTube X

© 2026 DeepNFTValue, Inc. All rights reserved.

Prediction markets for Agentic Evaluations

Is the "Promethean virus" in Large Language Models real?

Jun 7, 10:50 PMJan 1, 7:59 AM

10%chance

8141187

OptionVotes

YES

NO

29364

2889

SOAI#3: Open-ended agents make a meaningful scientific discovery end-to-end (hypothesis, expt, iteration, paper).

Oct 9, 11:04 PMOct 10, 11:04 PM

46%chance

384735

OptionVotes

YES

NO

1083

923

Will Musk pay the salaries of TSA agents during shutdown?

Mar 23, 11:26 AMMay 22, 11:20 AM

10%chance

313125

OptionVotes

YES

NO

3000

333

In what year will Al achieve 85% or higher score on the Humanity’s Last Exam benchmark?

Feb 7, 1:03 AMJan 2, 4:59 AM

162610

OptionProbability

2026

2027

2028

2029

2030-2034

2025

42

19

17

10

9

4

Will we see an open source LLM model better than Opus 4.5 before the end of 2026?

Jan 2, 6:14 PMDec 31, 11:59 PM

85.24%chance

142281

OptionVotes

NO

YES

2403

416

In what year will Al achieve 95% or higher score on the Humanity’s Last Exam benchmark?

Feb 7, 1:33 PMJan 2, 4:59 AM

81602

OptionProbability

2027

2029

2028

2030-2034

2026

2025

36

22

19

17

5

1

SOAI#1: A major retailer reports >5% of online sales from agentic checkout as AI agent advertising spend hits $5B.

Oct 9, 11:03 PMDec 31, 11:59 PM

26.72%chance

191273

OptionVotes

YES

NO

1656

604

Will a multi-agent system have its time horizon evaluated by METR before August 2026?

Feb 18, 6:17 PMJul 31, 11:59 PM

37.73%chance

111223

OptionVotes

YES

NO

1285

778

[Situational awareness] Will pre-2028 LLMs achieve token-output control?

Jul 9, 2:27 AMJan 2, 4:59 AM

38.5%chance

71195

OptionVotes

YES

NO

1264

791

Will Al achieve 95% or higher on the Humanity's Last Exam benchmark before 2027?

Feb 7, 12:50 AMDec 31, 4:59 PM

7.18%chance

12858

OptionVotes

YES

NO

395

76

Will a major US newspaper with at least 150 years of history partner with a top LLM (top ten by usage) by mid '29

Mar 7, 10:25 PMJul 1, 6:59 AM

56%chance

3128

OptionVotes

NO

YES

1128

886

Will an AI agent autonomously perform peer-review-quality LHC particle physics analysis by December 2029

Dec 23, 8:21 PMDec 31, 11:59 PM

54.55%chance

3121

OptionVotes

NO

YES

1351

1158

Latest stories