Recent AI progress on Epoch AI’s FrontierMath: Open Problems benchmark has accelerated, with multiple verified solutions to longstanding open math problems since mid-2026. Key drivers include Anthropic’s Claude variants (Fable 5 and others) producing solutions to the 2-adic absolute Galois group problem and a Hadamard matrix of order 668 in July–August, alongside OpenAI’s GPT-5.5 Pro and internal Astra models resolving additional number theory and conjecture problems. These outcomes reflect iterative gains in long-horizon reasoning, Lean formalization, and hybrid human-AI workflows rather than fully autonomous breakthroughs. Trader consensus favors near-term resolution to Yes because Epoch continues marking qualifying solves rapidly, though uncertainty remains around the exact timing of the next official classification and whether human contributions will disqualify borderline cases. Upcoming model updates and researcher experiments could provide further catalysts before year-end.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedNEW
Sep 15, 2026
September 15
43%
September 30
63%
$759 Vol.
September 15
$379 Vol.
43%
September 30
$379 Vol.
63%
This market will resolve to “Yes” if Epoch AI marks at least one additional FrontierMath: Open Problems problem as “Solved,” or otherwise officially states that such a problem has been solved, between market creation and the specified date 11:59 PM ET. Otherwise, this market will resolve to “No.”
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.Recent AI progress on Epoch AI’s FrontierMath: Open Problems benchmark has accelerated, with multiple verified solutions to longstanding open math problems since mid-2026. Key drivers include Anthropic’s Claude variants (Fable 5 and others) producing solutions to the 2-adic absolute Galois group problem and a Hadamard matrix of order 668 in July–August, alongside OpenAI’s GPT-5.5 Pro and internal Astra models resolving additional number theory and conjecture problems. These outcomes reflect iterative gains in long-horizon reasoning, Lean formalization, and hybrid human-AI workflows rather than fully autonomous breakthroughs. Trader consensus favors near-term resolution to Yes because Epoch continues marking qualifying solves rapidly, though uncertainty remains around the exact timing of the next official classification and whether human contributions will disqualify borderline cases. Upcoming model updates and researcher experiments could provide further catalysts before year-end.
This market will resolve to “Yes” if Epoch AI marks at least one additional FrontierMath: Open Problems problem as “Solved,” or otherwise officially states that such a problem has been solved, between market creation and the specified date 11:59 PM ET. Otherwise, this market will resolve to “No.”
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.
Market Opened: Aug 28, 2026, 6:20 PM ET
Volume
$759End Date
Sep 30, 2026Market Opened
Aug 28, 2026, 6:20 PM ETResolver
0x65070BE91...This market will resolve to “Yes” if Epoch AI marks at least one additional FrontierMath: Open Problems problem as “Solved,” or otherwise officially states that such a problem has been solved, between market creation and the specified date 11:59 PM ET. Otherwise, this market will resolve to “No.”
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.Recent AI progress on Epoch AI’s FrontierMath: Open Problems benchmark has accelerated, with multiple verified solutions to longstanding open math problems since mid-2026. Key drivers include Anthropic’s Claude variants (Fable 5 and others) producing solutions to the 2-adic absolute Galois group problem and a Hadamard matrix of order 668 in July–August, alongside OpenAI’s GPT-5.5 Pro and internal Astra models resolving additional number theory and conjecture problems. These outcomes reflect iterative gains in long-horizon reasoning, Lean formalization, and hybrid human-AI workflows rather than fully autonomous breakthroughs. Trader consensus favors near-term resolution to Yes because Epoch continues marking qualifying solves rapidly, though uncertainty remains around the exact timing of the next official classification and whether human contributions will disqualify borderline cases. Upcoming model updates and researcher experiments could provide further catalysts before year-end.
This market will resolve to “Yes” if Epoch AI marks at least one additional FrontierMath: Open Problems problem as “Solved,” or otherwise officially states that such a problem has been solved, between market creation and the specified date 11:59 PM ET. Otherwise, this market will resolve to “No.”
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.
Any problems that Epoch AI already classified as solved before market issuance will not qualify for resolution. Only problems newly classified by Epoch AI as solved after market issuance may qualify. If Epoch AI adds new problems to FrontierMath: Open Problems after market creation, those problems will be considered for resolution.
This market will resolve solely based on Epoch AI’s classification or official determination that a qualifying problem has been solved, regardless of the degree of artificial intelligence involvement. A verifier-accepted submission, publicly posted solution, partial result, or third-party claim will not qualify on its own unless Epoch AI recognizes the problem as solved.
The primary resolution source will be official information from Epoch AI, including https://epoch.ai/frontiermath/open-problems.
Volume
$759End Date
Sep 30, 2026Market Opened
Aug 28, 2026, 6:20 PM ETResolver
0x65070BE91...Recent AI progress on Epoch AI’s FrontierMath: Open Problems benchmark has accelerated, with multiple verified solutions to longstanding open math problems since mid-2026. Key drivers include Anthropic’s Claude variants (Fable 5 and others) producing solutions to the 2-adic absolute Galois group problem and a Hadamard matrix of order 668 in July–August, alongside OpenAI’s GPT-5.5 Pro and internal Astra models resolving additional number theory and conjecture problems. These outcomes reflect iterative gains in long-horizon reasoning, Lean formalization, and hybrid human-AI workflows rather than fully autonomous breakthroughs. Trader consensus favors near-term resolution to Yes because Epoch continues marking qualifying solves rapidly, though uncertainty remains around the exact timing of the next official classification and whether human contributions will disqualify borderline cases. Upcoming model updates and researcher experiments could provide further catalysts before year-end.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated
Beware of external links.
Beware of external links.
Frequently Asked Questions