OpenAI’s GPT-6 Astra Max currently leads the Code Arena WebDev leaderboard with an Arena score of 1800, outpacing Anthropic’s top entries by roughly 100–150 points as of mid-September 2026. This positioning reflects recent model releases and iterative gains in agentic web development tasks that emphasize multi-step reasoning, tool use, and frontend iteration. Anthropic’s Claude Fable 5.1 and Opus 5 variants briefly held the top spot earlier in the month before OpenAI’s update widened the gap. Lower-priced Chinese models such as Alibaba’s Qwen variants and Moonshot’s Kimi series sit close behind on the Pareto frontier but trail the leaders on raw performance. With resolution approaching in ten days, traders appear to view OpenAI’s demonstrated edge on the live human-voted benchmark as the dominant factor, while acknowledging that further updates or vote convergence could still shift relative rankings.
基於Polymarket數據的AI實驗性摘要。這不是交易建議，也不影響該市場的結算方式。 · 更新於OpenAI 68.8%
Anthropic 30%
Moonshot <1%
Google <1%
$158,570 交易量
$158,570 交易量
2026-09-30
OpenAI
69%
Anthropic
30%
Moonshot
1%
<1%
Z.ai
<1%
SpaceXAI
<1%
Meta
<1%
字節跳動
<1%
阿里巴巴
<1%
MiniMax
<1%
小米
<1%
DeepSeek
<1%
Thinky
<1%
騰訊
<1%
Poolside
<1%
Mistral
<1%
OpenAI 68.8%
Anthropic 30%
Moonshot <1%
Google <1%
$158,570 交易量
$158,570 交易量
2026-09-30
OpenAI
$32,109 交易量
69%
Anthropic
$66,158 交易量
30%
Moonshot
$21,031 交易量
1%
$7,896 交易量
<1%
Z.ai
$4,801 交易量
<1%
SpaceXAI
$6,591 交易量
<1%
Meta
$3,137 交易量
<1%
字節跳動
$1,134 交易量
<1%
阿里巴巴
$8,558 交易量
<1%
MiniMax
$1,246 交易量
<1%
小米
$657 交易量
<1%
DeepSeek
$2,690 交易量
<1%
Thinky
$560 交易量
<1%
騰訊
$571 交易量
<1%
Poolside
$641 交易量
<1%
Mistral
$789 交易量
<1%
This market will resolve according to the company that owns the model that has the highest rank based on the arena.ai Code Arena | WebDev Leaderboard when the table under "Code Arena | WebDev" filtered for "Models" is checked on September 30, 2026, 12:00 PM ET.
Results from the "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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".OpenAI’s GPT-6 Astra Max currently leads the Code Arena WebDev leaderboard with an Arena score of 1800, outpacing Anthropic’s top entries by roughly 100–150 points as of mid-September 2026. This positioning reflects recent model releases and iterative gains in agentic web development tasks that emphasize multi-step reasoning, tool use, and frontend iteration. Anthropic’s Claude Fable 5.1 and Opus 5 variants briefly held the top spot earlier in the month before OpenAI’s update widened the gap. Lower-priced Chinese models such as Alibaba’s Qwen variants and Moonshot’s Kimi series sit close behind on the Pareto frontier but trail the leaders on raw performance. With resolution approaching in ten days, traders appear to view OpenAI’s demonstrated edge on the live human-voted benchmark as the dominant factor, while acknowledging that further updates or vote convergence could still shift relative rankings.
This market will resolve according to the company that owns the model that has the highest rank based on the arena.ai Code Arena | WebDev Leaderboard when the table under "Code Arena | WebDev" filtered for "Models" is checked on September 30, 2026, 12:00 PM ET.
Results from the "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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 "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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".
市場開放時間： Jul 20, 2026, 7:23 PM ET
交易量
$158,570結束日期
2026-10-01市場開放時間
Jul 20, 2026, 7:23 PM ETThis market will resolve according to the company that owns the model that has the highest rank based on the arena.ai Code Arena | WebDev Leaderboard when the table under "Code Arena | WebDev" filtered for "Models" is checked on September 30, 2026, 12:00 PM ET.
Results from the "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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".OpenAI’s GPT-6 Astra Max currently leads the Code Arena WebDev leaderboard with an Arena score of 1800, outpacing Anthropic’s top entries by roughly 100–150 points as of mid-September 2026. This positioning reflects recent model releases and iterative gains in agentic web development tasks that emphasize multi-step reasoning, tool use, and frontend iteration. Anthropic’s Claude Fable 5.1 and Opus 5 variants briefly held the top spot earlier in the month before OpenAI’s update widened the gap. Lower-priced Chinese models such as Alibaba’s Qwen variants and Moonshot’s Kimi series sit close behind on the Pareto frontier but trail the leaders on raw performance. With resolution approaching in ten days, traders appear to view OpenAI’s demonstrated edge on the live human-voted benchmark as the dominant factor, while acknowledging that further updates or vote convergence could still shift relative rankings.
This market will resolve according to the company that owns the model that has the highest rank based on the arena.ai Code Arena | WebDev Leaderboard when the table under "Code Arena | WebDev" filtered for "Models" is checked on September 30, 2026, 12:00 PM ET.
Results from the "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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 "Rank" column under the "Code Arena | WebDev" Leaderboard tab at https://arena.ai/leaderboard/code/webdev (Overall) filtered for "Models" will be used to resolve this market.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by which model is listed higher on the leaderboard. 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., “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 arena.ai Code Arena | WebDev 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".
交易量
$158,570結束日期
2026-10-01市場開放時間
Jul 20, 2026, 7:23 PM ETOpenAI’s GPT-6 Astra Max currently leads the Code Arena WebDev leaderboard with an Arena score of 1800, outpacing Anthropic’s top entries by roughly 100–150 points as of mid-September 2026. This positioning reflects recent model releases and iterative gains in agentic web development tasks that emphasize multi-step reasoning, tool use, and frontend iteration. Anthropic’s Claude Fable 5.1 and Opus 5 variants briefly held the top spot earlier in the month before OpenAI’s update widened the gap. Lower-priced Chinese models such as Alibaba’s Qwen variants and Moonshot’s Kimi series sit close behind on the Pareto frontier but trail the leaders on raw performance. With resolution approaching in ten days, traders appear to view OpenAI’s demonstrated edge on the live human-voted benchmark as the dominant factor, while acknowledging that further updates or vote convergence could still shift relative rankings.
基於Polymarket數據的AI實驗性摘要。這不是交易建議，也不影響該市場的結算方式。 · 更新於
警惕外部連結哦。
警惕外部連結哦。
Frequently Asked Questions