• Questions
  • Tournaments
  • Services
  • News
  • Questions
  • Tournaments
  • Questions
  • Questions
Feed Home
👥
Communities
🏆
Leaderboards
Topics
❓
Top Questions
🗞️
In the News
🦾
AI Forecasting Benchmark
💎
Metaculus Cup
⏳
AI 2027
🌍
AI Pathways
🏛️
POTUS Predictions
categories
🦠
Health & Pandemics
🌱
Environment & Climate
☢️
Nuclear Technology & Risks
🤖
Artificial Intelligence
See all categories
  • About
  • API
  • FAQ
  • forecasting resources
  • For Journalists
  • Careers
GuidelinesPrivacy PolicyTerms of Use
ForbesScientific AmericanTimeVoxYale NewsNature
7 comments
23 forecasters

What will state-of-the-art top-1 accuracy on the APPS Benchmark introductory problems be from 2022 to 2025?

Contributed by the AI 2025 Forecasting Survey community.

0 comments
15 forecasters

What will be the best performance on SWE-bench Verified by December 31st 2025?

Current estimate
87.8 score

Contributed by the AI 2025 Forecasting Survey community.

1 comment
9 forecasters

What will be the best score on Cybench by December 31st 2025?

Current estimate
76.6%

Contributed by the AI 2025 Forecasting Survey community.

2 comments
11 forecasters

What will be the best performance on OSWorld by December 31st 2025?

Current estimate
70.1%

Q3 AI Benchmarking: Did Bots Outperform Human Forecasters?

12
1313 comments
7 comments
33 forecasters

What percent of ArXiv AI publications in the calendar year 2019 will be in the subcategory “Computation and Language”?

community
16
result
15.21
8 comments
30 forecasters

When will a computer program be listed as an author in journal article in the Annals of Mathematics?

Current estimate
06 Nov 2029
7 comments
53 forecasters

Will there be more ArXiv AI publications in the “Computation and Language” subcategory than in the “Computer Vision and Pattern Recognition” subcategory in the calendar year 2019?

resultNo

Computability and Complexity

16
11 comment
Metaculus Journal Archives

Tech Futures - 52 Conversation Starters

2
33 comments