Skip to main content
MANIFOLD
What will be true of the SOTA AI on the FrontierMath benchmark, before 2028?
11
Ṁ1.2kṀ2k
2028
88%
Over 1T parameters
80%
Transformer-based architecture
50%
Part of the AlphaProof family of models (AlphaProof N and variations)
37%
Developed by OpenAI
34%
Part of the GPT-N family of models (GPT-5, GPT-6, and variations)
31%
Developed by Google Deepmind
26%
Developed by Anthropic
25%
Narrow domain of knowledge. ie Does not know random facts such as when Google was founded, or who won the 1960 presidential election.
15%
Developed by a non-British and non-American company
10%
Energy-based Model (https://en.wikipedia.org/wiki/Energy-based_model)
10%
Part of the o1 family of models (o1, o2, etc. and variations)
9%
Based on Symbolic AI (https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)

An option resolves YES if it is true about the AI model, or program, known to be State of the Art in terms of the FrontierMath benchmark, at the end of the year 2027. It resolves NO otherwise.

You're welcome to add any interesting facts that might or might not be true about the state of the art in math problems, as defined by achieving the highest score on the FrontierMath benchmarks.

I reserve the right to cancel any option that is too vague, too improbable, etc.

See also:
/Bayesian/what-will-true-of-the-sota-ai-on-th-y0LE5uE9n9

/Bayesian/what-will-true-of-the-sota-ai-on-th-ROldIhZZgt
/Bayesian/what-will-true-of-the-sota-ai-on-th-RQptyR5uO8 (this market)

/Bayesian/will-an-ai-achieve-85-performance-o-hyPtIE98qZ

/MatthewBarnett/will-an-ai-achieve-85-performance-o

/Bayesian/will-an-ai-achieve-30-performance-o

Market context
Technology
AI
Technical AI Timelines
Math
IMO Grand Challenge
Get
Ṁ1,000
to start trading!

People are also trading

What will be true of the SOTA AI on the FrontierMath benchmark, before 2027?
Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?
44% chance
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
57% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
74% chance
Will AI models solve at least 2 FrontierMath Open Problems before 2027?
71% chance
By when will AI score >= 80% on FrontierMath
Will a frontier model score above 90% on the APEX-SWE benchmark before 2028?
48% chance
Will Al achieve 85% or higher score on the FrontierMath benchmark before 2030?
92% chance
SOTA AI at EOY 2026 a reasoning model?
94% chance
Will Al achieve 95% or higher score on the FrontierMath benchmark before 2030?
73% chance