Name: How high will AI score on ARC-AGI-2?
Start: 2025-04-11T18:08:46.832434Z
End: 2025-11-03T12:00:00Z

Use the internal polymarket geolocation service.

poly_geo

Improved notification preferences and types.

notifications_v2

funkit_deposit

funkit_withdraw

authenticated_book_ws

Improved in-game view for sports markets.

mobile_sports_overlay_v2

async_order_submission

Enable updates from the sports websocket.

sports_websocket

This is a market on predictions related to the advancements and implications of the second phase of the ARC AGI project.

This market will resolve to "Yes" if any team achieves a score of 85% or higher on the private evaluation set of ARC-AGI-2 by November 3, 2025 at 11:59 PM ET. Otherwise, this market will resolve to "No". 

Only scores publicly confirmed by ARC Prize will qualify. 

The resolution source will be official information from ARC Prize (https://arcprize.org). 

≥85% by November 3

This market will resolve to "Yes" if any team achieves a score of 20% or higher on the private evaluation set of ARC-AGI-2 by June 30, 2025 at 11:59 PM ET. Otherwise, this market will resolve to "No". 

Only scores publicly confirmed by ARC Prize will qualify. 

The resolution source will be official information from ARC Prize (https://arcprize.org). 

≥20% by June 30

This market will resolve to "Yes" if any team achieves a score of 30% or higher on the private evaluation set of ARC-AGI-2 by June 30, 2025 at 11:59 PM ET. Otherwise, this market will resolve to "No". 

Only scores publicly confirmed by ARC Prize will qualify. 

The resolution source will be official information from ARC Prize (https://arcprize.org). 

≥30% by June 30

This market will resolve to "Yes" if any team achieves a score of 20% or higher on the private evaluation set of ARC-AGI-2 by April 30, 2025 at 11:59 PM ET. Otherwise, this market will resolve to "No". 

Only scores publicly confirmed by ARC Prize will qualify. 

The resolution source will be official information from ARC Prize (https://arcprize.org). 

≥20% by April 30

How high will AI score on ARC-AGI-2?

The winners of the ARC Prize 2025 are scheduled to be publicly announced on December 5, 2025.

This market will resolve to "Yes" if any team achieves a score of 85% or higher on the private evaluation set of ARC-AGI-2 with the specified cost per task (CPT) by December 31, 2025, at 11:59 PM ET. Otherwise, this market will resolve to "No".

Only scores publicly confirmed by the ARC Prize will qualify.

If ARC Prize does not publicly the relevant data by December 31, 2025, at 11:59 PM ET, this market will resolve to “No”.

The resolution source will be official information from ARC Prize (https://arcprize.org).

Will anyone achieve an ARC-AGI score of 85% or higher at any cost per task?

This market will resolve to "Yes" if OpenAI or an official representative of the company announces that it has created an artificial general intelligence (AGI) by December 31, 2026 ET. Otherwise, this market will resolve to "No".

The primary resolution source for this market will be official information from OpenAI and/or its official representative, however a consensus of credible reporting will also be used.

OpenAI announces it has achieved AGI before 2027?

This market will resolve to "Yes" if OpenAI or an official representative of the company announces that it has created an artificial general intelligence (AGI) by December 31, 2025 ET. Otherwise, this market will resolve to "No".

The primary resolution source for this market will be official information from OpenAI and/or its official representative, however a consensus of credible reporting will also be used.


OpenAI announces it has achieved AGI in 2025?

This market will resolve to “No” if any of the following conditions are met between September 19, 2025, 6 PM ET, and December 31, 2025, 11:59 PM ET:

- Artificial Intelligence is named TIME's Person of 2025
- GPT-5 scores above 40% on Humanity’s Last Exam
- AI wins IMO gold medal
- AI model scores ≥ 90% on FrontierMath Benchmark
- AI scores ≥85% on ARC-AGI-2

Otherwise, this market will resolve to “Yes”.

If resolution-relevant information regarding the events mentioned above is not available by December 31, 2025, 11:59 PM ET, this market will remain open until January 31, 2026, 11:59 PM ET. If by that date there is still no clear information indicating that one of the listed events has occurred,  this market will resolve to “Yes”.

The full rules for this market can be found here:
https://polymarket-upload.s3.us-east-2.amazonaws.com/AI.png
https://polymarket-upload.s3.us-east-2.amazonaws.com/AI2.png

Nothing Ever Happens: AI Edition

This market will resolve to "Yes" if any model on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) reaches an Arena Score of 1500+ by December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No".

Results from the “Arena Score” section on the Leaderboard tab of https://lmarena.ai/ with the style control unchecked will be used to resolve this market.

The resolution source is the Chatbot Arena LLM Leaderboard at https://lmarena.ai/. If this source is temporarily unavailable, the market remains open until it is accessible again; if permanently unavailable, resolution will be based on another credible source.

Will any AI model reach 1500+ on Chatbot Arena by Dec 31?

This market will resolve to "Yes" if the listed company has the highest arena score on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) by December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No."

Results from the "Arena Score" section on the Leaderboard tab of https://lmarena.ai/ with the style control unchecked will be used to resolve this market.

If a listed modeI ties for #1 Arena score, it will suffice to resolve this market to "Yes."

The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://lmarena.ai/. If this resolution source becomes unavailable, the market will remain open until it is accessible again. If it becomes permanently unavailable, resolution will be based on another credible source.


Will Anthropic have a #1 AI model this year?

This market will resolve according to the listed entity which is the first to reach an Arena Score of 1500+ on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) by June 30, 2026, 11:59 PM ET. 

Results from the "Arena Score" section on the Leaderboard tab of https://lmarena.ai/ with the style control unchecked will be used to resolve this market.

If no company's model reaches 1500 Arena Score by the specified time, this market will resolve to "None by June 30".

If the first model to reach a 1500+ Arena Score belongs to any company other than the listed ones, this market will be resolved to "Other".

The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://lmarena.ai/. If this resolution source becomes unavailable, the market will remain open until it is accessible again. If it becomes permanently unavailable, resolution will be based on another credible source.

Will Google be the first company to have an AI model hit 1500 on Chatbot Arena by June 30 2026?

In November, a song reported to be the product of an AI-generated artist reached the top of the Billboard's Country Digital Song Sales chart. (see: https://www.barrons.com/news/ai-country-song-rollicks-to-the-top-of-us-sales-chart-7fe99e8a)

This market will resolve to "Yes" if any song widely reported to be entirely AI-generated reaches number 1 on any Billboard chart between November 13, 2025 and June 30, 2026, 11:59PM ET. Otherwise, this market will resolve to "No".

A song will be considered fully AI-generated if all vocals, musical composition, and production elements are created primarily by AI. Human actions such as prompting, mixing, and editing will not disqualify a song provided all audio content originates from AI.

Songs reported to have used AI-generated lyrics but not AI-generated voices, AI-assisted human vocals or instruments, or remixes, mash-ups, or covers using human-performed components will not be sufficient to resolve this market to "Yes".

The resolution source for this market will be a consensus of credible reporting.

Will another AI-generated song reach number 1 on any Billboard chart by June 30?

This market will resolve to "Yes" if the AI industry experiences an industry downturn by the specified date, 11:59 PM ET. Otherwise, this market will resolve to "No".

For the purposes of this market, the AI industry will be considered to have experienced an industry downturn once at least three of the following events have occurred within 90 days of this market's specified timeframe:
- NVIDIA Corporation (NVDA) closing stock price is down 50% from its all-time high.
- iShares PHLX Semiconductor ETF (SOXX) closing stock price is down 40% from its all-time high.
- OpenAI, Inc. or Anthropic PBC declares bankruptcy.
- OpenAI, Inc. is acquired.
- H100 rental price falls to $1.00 or lower for five consecutive days, as shown on the SiliconData Silicon Index at:
https://www.silicondata.com/products/silicon-index.
- Major AI Hardware Supplier Collapse: Taiwan Semiconductor Manufacturing Company Limited (TSM), ASML Holding N.V. (ASML), Broadcom Inc. (AVGO), Arista Networks, Inc. (ANET), or Super Micro Computer, Inc. (SMCI), closing stock price is down 50% from its all-time high.

This market may resolve immediately once three conditions have been met within 90 days of the specified timeframe.

This market will not resolve to "Yes" until three conditions have been met, regardless of reporting of an industry downturn or similar claims.

The primary resolution source will be official information from the respective companies and listing exchanges; however, a consensus of credible reporting will also be used.

AI Industry Downturn by December 31, 2026?

This market will resolve to "Yes" if Apple publicly announces a partnership with either OpenAI or Anthropic to use their AI models (such as ChatGPT or Claude) for enhancing or powering Siri on Apple devices by December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No".

The partnership must directly address Siri or voice assistant integration. General AI partnerships unrelated to Siri or non-specific mentions will not count.

The resolution source will be a consensus of credible reporting.

Apple Siri partnership with OpenAI/Anthropic by December 31?

This market will resolve to "Yes" if GPT-5 achieves a score of 70% or greater on the FrontierMath Exam by December 31, 2025, 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. 

GPT-5 scores ≥ 70% on FrontierMath Benchmark by December 31?

This market will resolve to the company which owns the model that has the top LiveBench “coding average” score, as based off the LiveBench AI model leaderboard (https://livebench.ai/#/), on December 31, 2025, 12:00 PM ET. 

If two models are tied for the top LiveBench coding average score at this market's check time, resolution will be based on whichever company's name, as it is described in this market group, comes first in alphabetical order.

The primary source of resolution for this market will be LiveBench’s AI leaderboard, specifically the “coding average” category, found at livebench.ai. If this resolution source is unavailable at check time, this market will remain open until the leaderboard comes back online and resolve based on the first check after it becomes available. If it becomes permanently unavailable, this market will resolve based on another resolution source.

Will OpenAI have the best AI model for coding at the end of 2025?

This market will resolve to "Yes" if at any point any Google Gemini 3 model has at least the specified arena score based on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/leaderboard/text) by December 31, 2025, 12:00 PM ET. Otherwise, this market will resolve to "No".

Results from the "Arena Score" section on the Leaderboard tab of https://lmarena.ai/leaderboard/text/overall-no-style-control with the style control off will be used to resolve this market.

The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://lmarena.ai/. If this resolution source is unavailable at check time, this market will remain open until the leaderboard comes back online and resolve based on the first check after it becomes available. If it becomes permanently unavailable, this market will resolve based on another resolution source.

Will any Google Gemini 3 model score at least 1500 on LMArena by December 31?

This market will resolve to "Yes" if, at any point before December 31, 2026, 11:59 PM ET, an AI model which is a Diffusion Large Language Model (dLLM) has the highest score based off the Chatbot Arena LLM Leaderboard (https://lmarena.ai/). Otherwise, this market will resolve to "No".

A Diffusion Large Language Model (dLLM) is any model for which official publicly released documentation, such as a model card, technical paper, or official statements from its developers, clearly identifies diffusion or iterative denoising as a central part of its text-generation or decoding process.

Results from the "Score" section on the Leaderboard tab of https://lmarena.ai/leaderboard/text set to default (style control on) will be used to resolve this market.

If two or models are tied for the top arena score at any point, this market will resolve to “Yes” if any of the joint-top ranked models are Diffusion Large Language Models.

The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://lmarena.ai/. If this resolution source is unavailable on December 31, 2026, 11:59 PM ET, this market will resolve based on all published Chatbot Arena LLM Leaderboard rankings prior to the period of lack of availability.

Will a dLLM be the top AI model before 2027?

This market will resolve to "Yes" if OpenAI achieves a public valuation of $1 trillion USD or more, or raises a private funding round that values the company at $1 trillion or more between June 22 and December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No."

To qualify, the valuation must be explicitly confirmed by OpenAI or an overwhelming consensus of credible reporting. 

The resolution source will be OpenAI’s official communications, however a consensus of credible reporting may also be used.

OpenAI $1T+ valuation in 2025?

Recent posts on X indicated that Meek Mill is looking for investors for an app. You can see more about that here: https://x.com/MeekMill/status/1962925141496598797

This market will resolve to "Yes" if Meek Mill launches an app advertised as making use of Artificial Intelligence by December 31, 2025, 11:59 PM PT. Otherwise, this market will resolve to "No".

Only an AI app which is confirmed to have been launched by or in affiliation with Meek Mill, either through posts from official social media channels, or otherwise confirmed by public statements will qualify.

The resolution source will be a consensus of credible reporting.

Meek Mill releases AI app in 2025?

This market will resolve to "Yes" if xAI's Grok 5 model is made available to the general public by December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No."

For this market to resolve to "Yes," Grok 5 must be launched and publicly accessible, including via open beta or open rolling waitlist signups. A closed beta or any form of private access will not suffice. The release must be clearly defined and publicly announced by Anthropic as being accessible to the general public.

Grok 5 refers to a product explicitly named Grok 5 (e.g. Grok 5.0 would count), or one that is recognized as a successor to Grok 4 similar to the progression from Grok 2 to Grok 3. Products labeled as Grok 4.5 or similar will not count for this market's resolution.

The primary resolution source for this market will be official information from xAI, with additional verification from a consensus of credible reporting.

Grok 5 released by March 31, 2026?

This market will resolve to the company which owns the model that has the highest “Mathematics Average” score on the LiveBench AI model leaderboard (https://livebench.ai/#/), on December 31, 2025, 12:00 PM ET. 

If two models are tied for the highest LiveBench Mathematics Average score at this market's check time, resolution will be based on whichever company's name, as it is described in this market group, comes first in alphabetical order.

The primary source of resolution for this market will be LiveBench’s AI leaderboard, specifically the “Mathematics Average” category, found at livebench.ai. If this resolution source is unavailable at check time, this market will remain open until the LiveBench AI leaderboard comes back online and will resolve based on the first check after it becomes available. If it becomes permanently unavailable, this market will resolve based on another resolution source.

Will Anthropic have the best AI model for math at the end of 2025?

This market will resolve to "Yes" if it is officially announced that xAI will be, has been, or is being acquired by or merged with Tesla (Tesla inc.) by December 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No".

An announcement by xAI will qualify for a "Yes" resolution, regardless of whether the announced acquisition/merger actually occurs.

The primary resolution source for this market will be official information from Tesla or xAI, however a consensus of credible reporting may also be used.

Will Tesla acquire xAI in 2025?

This market will resolve to “Yes” if all of the following conditions are met by January 31, 2026, 11:59 PM ET:

- Any model owned by Google has the highest arena score based on the Chatbot Arena LLM Leaderboard on January 31, 2026, 12:00 PM ET.
- Google Gemini 3 scores at least 40% on Humanity’s Last Exam
- Gemini 3 scores at least 40% on FrontierMath Benchmark

Otherwise, this market will resolve to “No”.

This market will remain open until it is confirmed that at least one of the above conditions has not been met, or until all of the above conditions have been met.

The full rules for this market can be found here:
https://polymarket-upload.s3.us-east-2.amazonaws.com/Google+Gemini+Parlay.pdf

How high will AI score on ARC-AGI-2?

≥20% by April 30
$19,487 Vol.
No

≥20% by June 30
$113,224 Vol.
No

≥30% by June 30
$10,781 Vol.
No

≥85% by November 3
$125,797 Vol.
No

Market Context

How high will AI score on ARC-AGI-2?

Rules

How high will AI score on ARC-AGI-2?

Market Context

How high will AI score on ARC-AGI-2?

About

Related

How high will AI score on ARC-AGI-2?

≥20% by April 30$19,487 Vol.Nocircle xmark

≥20% by June 30$113,224 Vol.Nocircle xmark

≥30% by June 30$10,781 Vol.Nocircle xmark

≥85% by November 3$125,797 Vol.Nocircle xmark

Market Context

How high will AI score on ARC-AGI-2?

Rules

How high will AI score on ARC-AGI-2?

Market Context

How high will AI score on ARC-AGI-2?

About

Related

≥20% by April 30
$19,487 Vol.
No

≥20% by June 30
$113,224 Vol.
No

≥30% by June 30
$10,781 Vol.
No

≥85% by November 3
$125,797 Vol.
No