OpenAI's GPT-5.4 Pro set a new FrontierMath record in early March 2026, achieving 38% on Tier 4—the benchmark's hardest research-level math problems—surpassing its own GPT-5.2 Pro's 31% from January and prior state-of-the-art scores below 20%. This leap reflects rapid scaling in large language model reasoning, with agents leveraging GPT-5.4 settling open FrontierMath problems, including elegant proofs of Erdős conjectures. OpenAI leads competitors like Anthropic's Claude 4.6 and xAI's Grok 4.2, which trail on this metric. Traders eye iterative releases like potential GPT-5.5 by June 30, alongside Epoch AI updates, as sustained progress could push scores toward 50% amid benchmark saturation risks.
Experimental AI-generated summary referencing Polymarket data · Updated$18,450 Vol.
Feb 28, 2026
60%+
49%
70%+
17%
$18,450 Vol.
60%+
$17,670 Vol.
49%
70%+
$780 Vol.
17%
This market will resolve to "Yes" if any OpenAI GPT model achieves the listed score or greater on the FrontierMath Exam by June 30, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.OpenAI's GPT-5.4 Pro set a new FrontierMath record in early March 2026, achieving 38% on Tier 4—the benchmark's hardest research-level math problems—surpassing its own GPT-5.2 Pro's 31% from January and prior state-of-the-art scores below 20%. This leap reflects rapid scaling in large language model reasoning, with agents leveraging GPT-5.4 settling open FrontierMath problems, including elegant proofs of Erdős conjectures. OpenAI leads competitors like Anthropic's Claude 4.6 and xAI's Grok 4.2, which trail on this metric. Traders eye iterative releases like potential GPT-5.5 by June 30, alongside Epoch AI updates, as sustained progress could push scores toward 50% amid benchmark saturation risks.
This market will resolve to "Yes" if any OpenAI GPT model achieves the listed score or greater on the FrontierMath Exam by June 30, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
Market Opened: Jan 29, 2026, 12:47 PM ET
Volume
$18,450End Date
Jun 30, 2026Market Opened
Jan 29, 2026, 12:47 PM ETResolver
0x65070BE91...This market will resolve to "Yes" if any OpenAI GPT model achieves the listed score or greater on the FrontierMath Exam by June 30, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.OpenAI's GPT-5.4 Pro set a new FrontierMath record in early March 2026, achieving 38% on Tier 4—the benchmark's hardest research-level math problems—surpassing its own GPT-5.2 Pro's 31% from January and prior state-of-the-art scores below 20%. This leap reflects rapid scaling in large language model reasoning, with agents leveraging GPT-5.4 settling open FrontierMath problems, including elegant proofs of Erdős conjectures. OpenAI leads competitors like Anthropic's Claude 4.6 and xAI's Grok 4.2, which trail on this metric. Traders eye iterative releases like potential GPT-5.5 by June 30, alongside Epoch AI updates, as sustained progress could push scores toward 50% amid benchmark saturation risks.
This market will resolve to "Yes" if any OpenAI GPT model achieves the listed score or greater on the FrontierMath Exam by June 30, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
Volume
$18,450End Date
Jun 30, 2026Market Opened
Jan 29, 2026, 12:47 PM ETResolver
0x65070BE91...OpenAI's GPT-5.4 Pro set a new FrontierMath record in early March 2026, achieving 38% on Tier 4—the benchmark's hardest research-level math problems—surpassing its own GPT-5.2 Pro's 31% from January and prior state-of-the-art scores below 20%. This leap reflects rapid scaling in large language model reasoning, with agents leveraging GPT-5.4 settling open FrontierMath problems, including elegant proofs of Erdős conjectures. OpenAI leads competitors like Anthropic's Claude 4.6 and xAI's Grok 4.2, which trail on this metric. Traders eye iterative releases like potential GPT-5.5 by June 30, alongside Epoch AI updates, as sustained progress could push scores toward 50% amid benchmark saturation risks.
Experimental AI-generated summary referencing Polymarket data · Updated
Beware of external links.
Beware of external links.
Frequently Asked Questions