**Close competition among frontier large language models keeps LiveBench Mathematics probabilities tightly bunched, with OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Fable 5/Opus variants trading near the top as of late July 2026.** Recent releases featuring high-effort “thinking” modes and specialized math tuning have narrowed gaps on contamination-free tasks, while Chinese models such as Kimi K3 and MiniMax trail but remain in contention on cost-adjusted scores. Traders weigh demonstrated benchmark gains against typical last-minute leaderboard volatility before the August 31 snapshot, noting that product timelines, inference optimizations, and new subtasks can still shift relative standings. The even odds reflect both the rapid iteration cycle and the benchmark’s resistance to saturation.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedOpenAI 45%
Anthropic 38%
Google 21%
DeepSeek 21%
NEW
NEW
Aug 31, 2026
OpenAI
45%
Anthropic
30%
21%
DeepSeek
21%
Xiaomi
20%
Moonshot
18%
ByteDance
18%
Alibaba
16%
SpaceXAI
14%
Meta
12%
Baidu
9%
Z.ai
9%
Thinky
6%
Nvidia
7%
Mistral
3%
Tencent
3%
Amazon
3%
Meituan
1%
StepFun
1%
Microsoft
1%
MiniMax
-
OpenAI 45%
Anthropic 38%
Google 21%
DeepSeek 21%
NEW
NEW
Aug 31, 2026
OpenAI
$128 Vol.
45%
Anthropic
$106 Vol.
30%
$67 Vol.
21%
DeepSeek
$67 Vol.
21%
Xiaomi
$67 Vol.
20%
Moonshot
$67 Vol.
18%
ByteDance
$89 Vol.
18%
Alibaba
$67 Vol.
16%
SpaceXAI
$67 Vol.
14%
Meta
$67 Vol.
12%
Baidu
$67 Vol.
9%
Z.ai
$67 Vol.
9%
Thinky
$138 Vol.
6%
Nvidia
$138 Vol.
7%
Mistral
$75 Vol.
3%
Tencent
$75 Vol.
3%
Amazon
$81 Vol.
3%
Meituan
$83 Vol.
1%
StepFun
$85 Vol.
1%
Microsoft
$92 Vol.
1%
MiniMax
$92 Vol.
-
This market will resolve according to the company which owns the model with the highest Mathematics score on LiveBench.ai when the leaderboard is checked on August 31, 2026, at 12:00 PM ET.
Results from the “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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.”**Close competition among frontier large language models keeps LiveBench Mathematics probabilities tightly bunched, with OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Fable 5/Opus variants trading near the top as of late July 2026.** Recent releases featuring high-effort “thinking” modes and specialized math tuning have narrowed gaps on contamination-free tasks, while Chinese models such as Kimi K3 and MiniMax trail but remain in contention on cost-adjusted scores. Traders weigh demonstrated benchmark gains against typical last-minute leaderboard volatility before the August 31 snapshot, noting that product timelines, inference optimizations, and new subtasks can still shift relative standings. The even odds reflect both the rapid iteration cycle and the benchmark’s resistance to saturation.
This market will resolve according to the company which owns the model with the highest Mathematics score on LiveBench.ai when the leaderboard is checked on August 31, 2026, at 12:00 PM ET.
Results from the “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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 “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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, 6:27 PM ET
Volume
$1,785End Date
Aug 31, 2026Market Opened
Jul 29, 2026, 6:27 PM ETResolution Source
https://livebench.ai/#/?cats=MathematicsResolver
0x69c47De9D...This market will resolve according to the company which owns the model with the highest Mathematics score on LiveBench.ai when the leaderboard is checked on August 31, 2026, at 12:00 PM ET.
Results from the “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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.”**Close competition among frontier large language models keeps LiveBench Mathematics probabilities tightly bunched, with OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Fable 5/Opus variants trading near the top as of late July 2026.** Recent releases featuring high-effort “thinking” modes and specialized math tuning have narrowed gaps on contamination-free tasks, while Chinese models such as Kimi K3 and MiniMax trail but remain in contention on cost-adjusted scores. Traders weigh demonstrated benchmark gains against typical last-minute leaderboard volatility before the August 31 snapshot, noting that product timelines, inference optimizations, and new subtasks can still shift relative standings. The even odds reflect both the rapid iteration cycle and the benchmark’s resistance to saturation.
This market will resolve according to the company which owns the model with the highest Mathematics score on LiveBench.ai when the leaderboard is checked on August 31, 2026, at 12:00 PM ET.
Results from the “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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 “Mathematics” column of the leaderboard at https://livebench.ai/#/?cats=Mathematics, with the latest available LiveBench release selected and the category set to “Mathematics,” 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
$1,785End Date
Aug 31, 2026Market Opened
Jul 29, 2026, 6:27 PM ETResolution Source
https://livebench.ai/#/?cats=MathematicsResolver
0x69c47De9D...**Close competition among frontier large language models keeps LiveBench Mathematics probabilities tightly bunched, with OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Fable 5/Opus variants trading near the top as of late July 2026.** Recent releases featuring high-effort “thinking” modes and specialized math tuning have narrowed gaps on contamination-free tasks, while Chinese models such as Kimi K3 and MiniMax trail but remain in contention on cost-adjusted scores. Traders weigh demonstrated benchmark gains against typical last-minute leaderboard volatility before the August 31 snapshot, noting that product timelines, inference optimizations, and new subtasks can still shift relative standings. The even odds reflect both the rapid iteration cycle and the benchmark’s resistance to saturation.
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