Skip to main content
icon for AI model scores ≥ 90% on FrontierMath Benchmark before 2027?

AI model scores ≥ 90% on FrontierMath Benchmark before 2027?

icon for AI model scores ≥ 90% on FrontierMath Benchmark before 2027?

AI model scores ≥ 90% on FrontierMath Benchmark before 2027?

Dec 31

Dec 31

23% chance
Polymarket

$66,253 Vol.

23% chance
Polymarket

$66,253 Vol.

This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No". The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used. Trader consensus prices a slim 23.5% chance of any AI model reaching 90% on the FrontierMath benchmark before 2027, reflecting the benchmark's design as a gauntlet of unsolved research-level math problems across Tiers 1-4 that have stymied even leading large language models. Top scores hover around 52% for OpenAI's GPT-5.5 Pro overall and 48% on the hardest Tier 4 via Google DeepMind's new multi-agent AI co-mathematician, which doubled prior baselines through stateful workflows and proof verification—yet still far from dominance. Epoch AI's May 12 review, where GPT-5.5 flagged fatal errors in roughly one-third of problems (mostly confirmed valid), signals potential score revisions downward. With 19 months left, rapid agentic gains offer upside, but sustained scaling plateaus and open-problem barriers sustain skepticism absent major architectural breakthroughs or upcoming releases like GPT-5.6.

This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".

The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used.
Volume
$66,253
End Date
Dec 31, 2026
Market Opened
Nov 12, 2025, 5:15 PM ET
This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No". The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used.
This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No". The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used. Trader consensus prices a slim 23.5% chance of any AI model reaching 90% on the FrontierMath benchmark before 2027, reflecting the benchmark's design as a gauntlet of unsolved research-level math problems across Tiers 1-4 that have stymied even leading large language models. Top scores hover around 52% for OpenAI's GPT-5.5 Pro overall and 48% on the hardest Tier 4 via Google DeepMind's new multi-agent AI co-mathematician, which doubled prior baselines through stateful workflows and proof verification—yet still far from dominance. Epoch AI's May 12 review, where GPT-5.5 flagged fatal errors in roughly one-third of problems (mostly confirmed valid), signals potential score revisions downward. With 19 months left, rapid agentic gains offer upside, but sustained scaling plateaus and open-problem barriers sustain skepticism absent major architectural breakthroughs or upcoming releases like GPT-5.6.

This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No".

The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used.
Volume
$66,253
End Date
Dec 31, 2026
Market Opened
Nov 12, 2025, 5:15 PM ET
This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No". The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used.

Beware of external links.

Frequently Asked Questions

"AI model scores ≥ 90% on FrontierMath Benchmark before 2027?" is a prediction market on Polymarket where traders buy and sell "Yes" or "No" shares based on whether they believe this event will happen. The current crowd-sourced probability is 23% for "Yes." For example, if "Yes" is priced at 23¢, the market collectively assigns a 23% chance that this event will occur. These odds shift continuously as traders react to new developments and information. Shares in the correct outcome are redeemable for $1 each upon market resolution.

As of today, "AI model scores ≥ 90% on FrontierMath Benchmark before 2027?" has generated $66.3K in total trading volume since the market launched on Nov 12, 2025. This level of trading activity reflects strong engagement from the Polymarket community and helps ensure that the current odds are informed by a deep pool of market participants. You can track live price movements and trade on any outcome directly on this page.

To trade on "AI model scores ≥ 90% on FrontierMath Benchmark before 2027?," simply choose whether you believe the answer is "Yes" or "No." Each side has a current price that reflects the market's implied probability. Enter your amount and click "Trade." If you buy "Yes" shares and the outcome resolves as "Yes," each share pays out $1. If it resolves as "No," your "Yes" shares pay $0. You can also sell your shares at any time before resolution if you want to lock in a profit or cut a loss.

The current probability for "AI model scores ≥ 90% on FrontierMath Benchmark before 2027?" is 23% for "Yes." This means the Polymarket crowd currently believes there is a 23% chance that this event will occur. These odds update in real-time based on actual trades, providing a continuously updated signal of what the market expects to happen.

The resolution rules for "AI model scores ≥ 90% on FrontierMath Benchmark before 2027?" define exactly what needs to happen for each outcome to be declared a winner — including the official data sources used to determine the result. You can review the complete resolution criteria in the "Rules" section on this page above the comments. We recommend reading the rules carefully before trading, as they specify the precise conditions, edge cases, and sources that govern how this market is settled.