Skip to main content
Market icon
科技·AI

AI模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？

Market icon
科技·AI

AI模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？

12月 31

12月 31

是

22% 機率
Polymarket

$47,297 交易量

是

22% 機率
Polymarket

$47,297 交易量

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 76% implied probability on "No" for an AI model reaching 90% on the FrontierMath benchmark before 2027, as leading large language models like OpenAI's GPT-5.4 (47.6% overall, 38% on Tier 4) and Anthropic's Claude Opus 4.6 (40% on Tiers 1-3) remain well below the threshold despite rapid scaling gains—from low single digits in late 2025 to mid-30s by early 2026. Epoch AI's challenging problems, including unsolved research-level math vetted by experts, demand novel reasoning beyond pattern matching, with progress slowing on Tier 4's 50 ultra-hard items. OpenAI's April 15 purchase of verifiers for FrontierMath open problems underscores competitive push, but upcoming releases like GPT-5.5 or equivalents face timeline uncertainties and potential diminishing returns, keeping odds grounded.

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.
交易量
$47,297
結束日期
2026-12-31
市場開放時間
Nov 12, 2025, 5:15 PM ET

Resolver

0x65070BE91...
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 76% implied probability on "No" for an AI model reaching 90% on the FrontierMath benchmark before 2027, as leading large language models like OpenAI's GPT-5.4 (47.6% overall, 38% on Tier 4) and Anthropic's Claude Opus 4.6 (40% on Tiers 1-3) remain well below the threshold despite rapid scaling gains—from low single digits in late 2025 to mid-30s by early 2026. Epoch AI's challenging problems, including unsolved research-level math vetted by experts, demand novel reasoning beyond pattern matching, with progress slowing on Tier 4's 50 ultra-hard items. OpenAI's April 15 purchase of verifiers for FrontierMath open problems underscores competitive push, but upcoming releases like GPT-5.5 or equivalents face timeline uncertainties and potential diminishing returns, keeping odds grounded.

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.
交易量
$47,297
結束日期
2026-12-31
市場開放時間
Nov 12, 2025, 5:15 PM ET

Resolver

0x65070BE91...
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.

警惕外部連結哦。

Frequently Asked Questions

"AI模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？" is a prediction market on Polymarket with 2 possible outcomes where traders buy and sell shares based on what they believe will happen. The current leading outcome is "AI模型在2027年前於FrontierMath基準測試中得分≥90%？" at 22%. Prices reflect real-time crowd-sourced probabilities. For example, a share priced at 22¢ implies that the market collectively assigns a 22% chance to that outcome. 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模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？" has generated $47.3K 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模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？," browse the 2 available outcomes listed on this page. Each outcome displays a current price representing the market's implied probability. To take a position, select the outcome you believe is most likely, choose "Yes" to trade in favor of it or "No" to trade against it, enter your amount, and click "Trade." If your chosen outcome is correct when the market resolves, your "Yes" shares pay out $1 each. If it's incorrect, they pay out $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 frontrunner for "AI模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？" is "AI模型在2027年前於FrontierMath基準測試中得分≥90%？" at 22%, meaning the market assigns a 22% chance to that outcome. These odds update in real-time as traders buy and sell shares, so they reflect the latest collective view of what's most likely to happen. Check back frequently or bookmark this page to follow how the odds shift as new information emerges.

The resolution rules for "AI模型在2027年之前在FrontierMath Benchmark上的得分≥ 90% ？" 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.