TOTAL VOLUME:
$134b
24H VOL:
$107,351,958
24H TRANSACTIONS:
2,388,728,490
OPEN INTEREST:
$1,416,970,024
400,720
Markets across
30,097
events
MATCHED EVENTS:
2,633
PLATFORM COVERAGE:
5
Polymarket:
39%
VS.
Kalshi:
61%
Closed: Feb 27, 7:00 PM EST
Polymarket
This market tracks whether any OpenAI GPT model will reach a 60% score threshold on the FrontierMath Exam, a rigorous mathematics benchmark. On Polymarket, the leading outcome carries a 65.0% probability, while a higher 70% threshold outcome stands at 17.5%. Resolution will be determined by Epoch AI's Frontier Math leaderboard for Tier 1-3 benchmarks, with credible reporting serving as a secondary source. Watch for OpenAI model submissions and score updates on the Epoch AI leaderboard leading up to the June 30, 2026 deadline.
This market will resolve to "Yes" if any OpenAI GPT model achieves the listed score or greater on the FrontierMath Exam by February 28, 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.
On Polymarket, this event is priced as a binary contract: Will any OpenAI GPT model score at least 60% on the FrontierMath Exam? On Polymarket, prices reflect that venue's order book, liquidity, and how traders price the outcome right now. The current market probability reflects trader expectations about OpenAI's model advancement and benchmark performance by the resolution date. Prices fluctuate based on new model releases, benchmark results, and technical developments in large language models. Traders buy YES contracts if bullish on OpenAI's mathematical reasoning capabilities, or NO contracts if skeptical, with the spread between bid and ask prices indicating market confidence in the outcome.
The market resolves on Jun 30, 2026, establishing a final deadline for determining whether the outcome has occurred. Resolution hinges on official FrontierMath Exam results published by the benchmark administrators, specifically whether any OpenAI GPT model achieves at least 60% on the test. The outcome is binary: either the threshold is met or it is not. Traders should monitor OpenAI announcements, benchmark publications, and model release dates leading up to the resolution window to assess the likelihood of success.
Key catalysts include new OpenAI model releases or capability announcements, particularly any GPT versions optimized for mathematical reasoning. Publication of FrontierMath benchmark results for competing models provides context for OpenAI's likely performance. Technical breakthroughs in reasoning or symbolic mathematics, industry research papers, and OpenAI's official statements about model development timelines can shift trader expectations. Interim benchmark scores or leaks, changes in AI safety or deployment policies, and broader AI industry developments may also influence market pricing as traders reassess the probability of achieving 60% by Jun 30, 2026.