Anthropic's Claude Fable 5 and Opus 4.8/5 series models currently post the strongest coding-specific results on LiveBench variants, including high marks on code generation and completion subtasks, driving the 87.5% market-implied probability. OpenAI's o3-mini and GPT-5.x family lead overall LiveBench scores near 84-87% as of September 21 but trail in several coding-focused breakdowns, consistent with the 10.8% odds. Recent September releases and max-effort evaluations from both labs have tightened the gap, while lower-priced Chinese models like Qwen3 and GLM variants remain competitive on cost-adjusted metrics but lag frontier coding benchmarks. With resolution imminent, traders are weighting demonstrated coding agentic performance and latest official updates most heavily.
Eksperymentalne podsumowanie AI odwołujące się do danych Polymarket. To nie jest porada handlowa i nie ma wpływu na rozstrzyganie tego rynku. · ZaktualizowanoWhich company has the best AI model on LiveBench (Coding) end of September?
Which company has the best AI model on LiveBench (Coding) end of September?
Anthropic 87.7%
OpenAI 10.8%
SpaceXAI 1.6%
Meta <1%
$62,173 Wol.
$62,173 Wol.
Sep 30, 2026
Anthropic
88%
OpenAI
11%
SpaceXAI
2%
Meta
<1%
<1%
Alibaba
<1%
Moonshot
<1%
Baidu
<1%
Z.ai
<1%
Xiaomi
<1%
DeepSeek
<1%
Amazon
<1%
ByteDance
<1%
Nvidia
<1%
Thinky
<1%
MiniMax
<1%
Mistral
<1%
Meituan
<1%
Tencent
<1%
StepFun
<1%
Microsoft
<1%
Anthropic 87.7%
OpenAI 10.8%
SpaceXAI 1.6%
Meta <1%
$62,173 Wol.
$62,173 Wol.
Sep 30, 2026
Anthropic
$21,896 Wol.
88%
OpenAI
$20,318 Wol.
11%
SpaceXAI
$3,129 Wol.
2%
Meta
$3,162 Wol.
<1%
$378 Wol.
<1%
Alibaba
$777 Wol.
<1%
Moonshot
$791 Wol.
<1%
Baidu
$517 Wol.
<1%
Z.ai
$1,144 Wol.
<1%
Xiaomi
$838 Wol.
<1%
DeepSeek
$810 Wol.
<1%
Amazon
$860 Wol.
<1%
ByteDance
$886 Wol.
<1%
Nvidia
$1,293 Wol.
<1%
Thinky
$811 Wol.
<1%
MiniMax
$912 Wol.
<1%
Mistral
$428 Wol.
<1%
Meituan
$1,096 Wol.
<1%
Tencent
$937 Wol.
<1%
StepFun
$839 Wol.
<1%
Microsoft
$348 Wol.
<1%
This market will resolve according to the company which owns the model with the highest Coding score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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's Claude Fable 5 and Opus 4.8/5 series models currently post the strongest coding-specific results on LiveBench variants, including high marks on code generation and completion subtasks, driving the 87.5% market-implied probability. OpenAI's o3-mini and GPT-5.x family lead overall LiveBench scores near 84-87% as of September 21 but trail in several coding-focused breakdowns, consistent with the 10.8% odds. Recent September releases and max-effort evaluations from both labs have tightened the gap, while lower-priced Chinese models like Qwen3 and GLM variants remain competitive on cost-adjusted metrics but lag frontier coding benchmarks. With resolution imminent, traders are weighting demonstrated coding agentic performance and latest official updates most heavily.
This market will resolve according to the company which owns the model with the highest Coding score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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 “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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.”
Rynek otwarty: Jul 29, 2026, 6:17 PM ET
Wolumen
$62,173Data zakończenia
Oct 1, 2026Rynek otwarty
Jul 29, 2026, 6:17 PM ETŹródło rozstrzygnięcia
https://livebench.ai/#/?cats=CodingRozstrzygający
0x69c47De9D...This market will resolve according to the company which owns the model with the highest Coding score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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's Claude Fable 5 and Opus 4.8/5 series models currently post the strongest coding-specific results on LiveBench variants, including high marks on code generation and completion subtasks, driving the 87.5% market-implied probability. OpenAI's o3-mini and GPT-5.x family lead overall LiveBench scores near 84-87% as of September 21 but trail in several coding-focused breakdowns, consistent with the 10.8% odds. Recent September releases and max-effort evaluations from both labs have tightened the gap, while lower-priced Chinese models like Qwen3 and GLM variants remain competitive on cost-adjusted metrics but lag frontier coding benchmarks. With resolution imminent, traders are weighting demonstrated coding agentic performance and latest official updates most heavily.
This market will resolve according to the company which owns the model with the highest Coding score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET.
Results from the “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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 “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” 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.”
Wolumen
$62,173Data zakończenia
Oct 1, 2026Rynek otwarty
Jul 29, 2026, 6:17 PM ETŹródło rozstrzygnięcia
https://livebench.ai/#/?cats=CodingRozstrzygający
0x69c47De9D...Anthropic's Claude Fable 5 and Opus 4.8/5 series models currently post the strongest coding-specific results on LiveBench variants, including high marks on code generation and completion subtasks, driving the 87.5% market-implied probability. OpenAI's o3-mini and GPT-5.x family lead overall LiveBench scores near 84-87% as of September 21 but trail in several coding-focused breakdowns, consistent with the 10.8% odds. Recent September releases and max-effort evaluations from both labs have tightened the gap, while lower-priced Chinese models like Qwen3 and GLM variants remain competitive on cost-adjusted metrics but lag frontier coding benchmarks. With resolution imminent, traders are weighting demonstrated coding agentic performance and latest official updates most heavily.
Eksperymentalne podsumowanie AI odwołujące się do danych Polymarket. To nie jest porada handlowa i nie ma wpływu na rozstrzyganie tego rynku. · Zaktualizowano
Uważaj na linki zewnętrzne.
Uważaj na linki zewnętrzne.
Często zadawane pytania