Question

By what date will an AI system demonstrate human-level accuracy in extracting data from all types of charts in documents?

5 comments5

Total Forecasters14

Community Prediction2025-08

Make a Prediction

My Prediction

community

<2024-03

lower 25%

median

upper 75%

>2030-01

...

3.1%

2025-02

2025-08

2026-11

10.6%

Authors:

standupre

Opened:

Closes:

Scheduled resolution:

Artificial Intelligence

Artificial intelligence

Computer science

Linguistics

Bag-of-words model in computer vision

Pediatrics

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

80%

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

2025-06

Comments

? comments

Authors:

standupre

Opened:

Closes:

Scheduled resolution:

Artificial Intelligence

Artificial intelligence

Computer science

Linguistics

Bag-of-words model in computer vision

Pediatrics

Why is ChatGPT so bad at math?

TechCrunch•Oct 2, 2024

'A lot of money is going to get wasted': MIT economist sounds the alarm on AI hype

Business Insider•Oct 2, 2024

The Cognitive Disconnect Between Physicians and AI

Psychology Today•Oct 3, 2024

Learn more about Metaculus NewsMatch

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

80%

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

2025-06

MetaculusM

🚀Metaculus Open-Source Rewrite is Live!

By what date will an AI system demonstrate human-level accuracy in extracting data from all types of charts in documents?

Make a Prediction

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

Comments

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

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

Will OpenAI release an LLM product or API that hallucinates 5x less than GPT-4 did when it was released, by June 30, 2025?

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?