Benchmark News

Hut 8 Unveils 1.5-GW U.S. Build-Out; Benchmark Ups Target

5 months ago

Semtech Gains as Q2 Beat Spurs Cluster of Price-Target Hikes

Company Earnings

Stocks

Business

Semtech Gains as Q2 Beat Spurs Cluster of Price-Target Hikes

5 months ago

Madrona Unveils 2025 IA40, Spotlighting 40 Rising AI Startups

AI Products

AI Fundraising

Madrona Unveils 2025 IA40, Spotlighting 40 Rising AI Startups

5 months ago

Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?

Nov 8, 8:25 PMJan 2, 7:59 AM

62.22%chance

270269974

OptionVotes

YES

5677

4517

By 2029, will any AI be able to read a novel and reliably answer questions about it? (Gary Marcus benchmark #2)

Sep 16, 8:34 PMJan 1, 8:00 AM

85.82%chance

12253569

OptionVotes

YES

1602

1470

Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?

Nov 8, 11:52 PMJan 2, 7:59 AM

35%chance

9038240

OptionVotes

YES

1363

734

By 2029 will any AI be able to watch a movie and accurately tell you what is going on? (Gary Marcus benchmark #1)

Sep 16, 8:33 PMJan 1, 8:00 AM

86.75%chance

9327406

OptionVotes

YES

1872

1109

In 2029, will any AI be able to construct "reasonably" bug-free code of >= 10k LOC from a natural language specification? (Gary Marcus benchmark #4)

Sep 16, 8:43 PMJan 1, 8:00 AM

90.97%chance

11626804

OptionVotes

YES

2867

552

In 2029, will any AI be able to take an arbitrary proof in the mathematical literature and translate it into a form suitable for symbolic verification? (Gary Marcus benchmark #5)

Sep 16, 8:47 PMJan 1, 8:00 AM

75.9%chance

10318919

OptionVotes

YES

1813

773

In 2029, will any AI be able to work as a competent cook in an arbitrary kitchen? (Gary Marcus benchmark #3)

Sep 16, 8:37 PMJan 1, 8:00 AM

55.76%chance

11515166

OptionVotes

YES

1880

1102

On January 1, 2027, a Transformer-like model will continue to hold the state-of-the-art position in most benchmark

Jun 13, 9:21 AMDec 31, 9:59 PM

88.63%chance

436111

OptionVotes

YES

2699

255

Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?

Feb 7, 7:34 PMJan 1, 7:59 AM

45.67%chance

456069

OptionVotes

YES

1094

919

Will AIs beat human experts in question-answering on the GPQA benchmark before January 1st, 2027?

Jan 18, 12:11 AMJan 2, 7:59 AM

94.58%chance

304337

OptionVotes

YES

3928

505

Will at least 3 of the Gary Marcus benchmark questions resolve YES?

Sep 16, 9:19 PMJan 1, 8:00 AM

92.22%chance

443615

OptionVotes

YES

2380

769

Benchmark Gap #3: Once a model achieves superhuman performance on a competitive programming benchmark, will it be less than 2 years before there are "entry level" AI programmers in industry use?

Apr 8, 6:06 PMJan 1, 4:59 AM

78%chance

16943

OptionVotes

YES

1382

859

Latest stories

Aug 28, 2025
Aug 28, 2025
VC
AI Products
AI Fundraising
Madrona Unveils 2025 IA40, Spotlighting 40 Rising AI Startups
Authors
8
5 months ago
Aug 27, 2025
Aug 27, 2025
Stocks
Mining
Business
Hut 8 Unveils 1.5-GW U.S. Build-Out; Benchmark Ups Target
Authors
5
5 months ago
Aug 26, 2025
Aug 26, 2025
Company Earnings
Stocks
Business
Semtech Gains as Q2 Beat Spurs Cluster of Price-Target Hikes
Authors
9
5 months ago

Join our channels

Get the latest stories live on any device.

WhatsApp
Top Stories
Join
Telegram
Top Stories
Join

Benchmark News

Top stories

Prediction markets for Benchmark

Prediction markets for Benchmark

Prediction markets for Benchmark

Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?

By 2029, will any AI be able to read a novel and reliably answer questions about it? (Gary Marcus benchmark #2)

Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?

By 2029 will any AI be able to watch a movie and accurately tell you what is going on? (Gary Marcus benchmark #1)

In 2029, will any AI be able to construct "reasonably" bug-free code of >= 10k LOC from a natural language specification? (Gary Marcus benchmark #4)

In 2029, will any AI be able to take an arbitrary proof in the mathematical literature and translate it into a form suitable for symbolic verification? (Gary Marcus benchmark #5)

In 2029, will any AI be able to work as a competent cook in an arbitrary kitchen? (Gary Marcus benchmark #3)

On January 1, 2027, a Transformer-like model will continue to hold the state-of-the-art position in most benchmark

Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?

Will AIs beat human experts in question-answering on the GPQA benchmark before January 1st, 2027?

Will at least 3 of the Gary Marcus benchmark questions resolve YES?

Benchmark Gap #3: Once a model achieves superhuman performance on a competitive programming benchmark, will it be less than 2 years before there are "entry level" AI programmers in industry use?

Latest stories

Join our channels

WhatsApp

Telegram