Anthropic holds an 87% implied probability of topping LiveBench overall at month-end because its Claude Fable 5.1 and Opus 5 variants have posted the strongest verified scores across recent dynamic snapshots, outpacing OpenAI’s o3-mini and GPT-5.5 families on the benchmark’s contamination-resistant tasks. Traders view the gap as durable given Anthropic’s consistent edge in reasoning and agentic categories through September 22, with no new model releases or major updates expected before resolution on September 30. OpenAI’s 12% odds reflect solid but trailing results from its latest mini and Sol series, while all other labs sit below 1% on the expectation that current frontier gaps will hold through the final days of the evaluation window.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedAnthropic 87%
OpenAI 12.2%
DeepSeek <1%
Meta <1%
$64,354 Vol.
$64,354 Vol.
Sep 30, 2026
Anthropic
87%
OpenAI
12%
DeepSeek
1%
Meta
1%
SpaceXAI
<1%
<1%
Alibaba
<1%
Moonshot
<1%
Baidu
<1%
Z.ai
<1%
Xiaomi
<1%
Amazon
<1%
ByteDance
<1%
Nvidia
<1%
Thinky
<1%
MiniMax
<1%
Mistral
<1%
Meituan
<1%
Tencent
<1%
StepFun
<1%
Microsoft
<1%
Anthropic 87%
OpenAI 12.2%
DeepSeek <1%
Meta <1%
$64,354 Vol.
$64,354 Vol.
Sep 30, 2026
Anthropic
$20,026 Vol.
87%
OpenAI
$15,631 Vol.
12%
DeepSeek
$1,655 Vol.
1%
Meta
$2,967 Vol.
1%
SpaceXAI
$2,724 Vol.
<1%
$2,677 Vol.
<1%
Alibaba
$2,307 Vol.
<1%
Moonshot
$2,171 Vol.
<1%
Baidu
$706 Vol.
<1%
Z.ai
$2,337 Vol.
<1%
Xiaomi
$989 Vol.
<1%
Amazon
$836 Vol.
<1%
ByteDance
$681 Vol.
<1%
Nvidia
$790 Vol.
<1%
Thinky
$722 Vol.
<1%
MiniMax
$1,233 Vol.
<1%
Mistral
$2,467 Vol.
<1%
Meituan
$1,108 Vol.
<1%
Tencent
$806 Vol.
<1%
StepFun
$488 Vol.
<1%
Microsoft
$1,031 Vol.
<1%
This market will resolve according to the company which owns the model with the highest Overall score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”Anthropic holds an 87% implied probability of topping LiveBench overall at month-end because its Claude Fable 5.1 and Opus 5 variants have posted the strongest verified scores across recent dynamic snapshots, outpacing OpenAI’s o3-mini and GPT-5.5 families on the benchmark’s contamination-resistant tasks. Traders view the gap as durable given Anthropic’s consistent edge in reasoning and agentic categories through September 22, with no new model releases or major updates expected before resolution on September 30. OpenAI’s 12% odds reflect solid but trailing results from its latest mini and Sol series, while all other labs sit below 1% on the expectation that current frontier gaps will hold through the final days of the evaluation window.
This market will resolve according to the company which owns the model with the highest Overall score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”
Market Opened: Jul 29, 2026, 6:13 PM ET
Volume
$64,354End Date
Sep 30, 2026Market Opened
Jul 29, 2026, 6:13 PM ETResolution Source
https://livebench.ai/Resolver
0x69c47De9D...This market will resolve according to the company which owns the model with the highest Overall score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”Anthropic holds an 87% implied probability of topping LiveBench overall at month-end because its Claude Fable 5.1 and Opus 5 variants have posted the strongest verified scores across recent dynamic snapshots, outpacing OpenAI’s o3-mini and GPT-5.5 families on the benchmark’s contamination-resistant tasks. Traders view the gap as durable given Anthropic’s consistent edge in reasoning and agentic categories through September 22, with no new model releases or major updates expected before resolution on September 30. OpenAI’s 12% odds reflect solid but trailing results from its latest mini and Sol series, while all other labs sit below 1% on the expectation that current frontier gaps will hold through the final days of the evaluation window.
This market will resolve according to the company which owns the model with the highest Overall score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”
Results from the “Overall” column of the leaderboard at https://livebench.ai/, with the latest available LiveBench release selected and the category set to “All,” will be used to resolve this market.
Models will be ranked according to the specified score, with higher scores ranked ahead of lower scores. If two or more models have exactly the same score as displayed on the leaderboard, the model with the lower listed "cost per successful task" will be ranked ahead. If a tie still remains, alphabetical order of company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact score and cost per successful task, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies first place under this ranking.
The resolution source for this market is the LiveBench leaderboard. If this resolution source is unavailable at check time, this market will remain open until the 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 to “Other.”
Volume
$64,354End Date
Sep 30, 2026Market Opened
Jul 29, 2026, 6:13 PM ETResolution Source
https://livebench.ai/Resolver
0x69c47De9D...Anthropic holds an 87% implied probability of topping LiveBench overall at month-end because its Claude Fable 5.1 and Opus 5 variants have posted the strongest verified scores across recent dynamic snapshots, outpacing OpenAI’s o3-mini and GPT-5.5 families on the benchmark’s contamination-resistant tasks. Traders view the gap as durable given Anthropic’s consistent edge in reasoning and agentic categories through September 22, with no new model releases or major updates expected before resolution on September 30. OpenAI’s 12% odds reflect solid but trailing results from its latest mini and Sol series, while all other labs sit below 1% on the expectation that current frontier gaps will hold through the final days of the evaluation window.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated
Beware of external links.
Beware of external links.
Frequently Asked Questions