MetaculusM

Questions
Tournaments

Leaderboards
News
create

AI Benchmarking

Topics

categories

See all categories

About
API

FAQ
forecasting resources
For Journalists

Careers

Guidelines Privacy Policy Terms of Use

On January 1, 2025, which frontier AI lab will have a publicly available model with the highest score on the MMLU benchmark?

Google DeepMind

9

Understanding AI With Timothy B. Lee

Will AI capabilities plateau with the next generation (GPT-5, etc.) of language models?

Google DeepMind / Gemini 2 Ultra

Anthropic / Claude 4 Opus

20

Will the listed AI companies/labs pause any of their models before January 1st, 2025 because they detect dangerous capabilities?

Google DeepMind

12

What type of research group will develop the first transformative AI?

17

Situational Awareness

Will the listed AI companies/labs practice implementing emergency response plans before January 1st, 2025?

Google DeepMind

5

Will the listed AI companies/labs create a board risk committee before January 1st, 2025?

Google DeepMind

3

Will the listed AI companies/labs have merge and assist clauses on January 1st 2025?

Google DeepMind

4

3 AI labs constrain capabilities before 2026?

Date of Artificial General Intelligence

Date of Artificial General Intelligence

7

LLM passes ARA before 2025?

LLM training paused for dangerous capability? (OpenAI)

LLM training paused for dangerous capability? (OpenAI)

6

Conditional Cup

Will the highest Elo LLM on Chatbot Arena be non-proprietary during 2024?

8