Traders see no dominant leader in image-to-video AI as the October deadline approaches, with market-implied odds clustered near 50% across most entrants. Recent Artificial Analysis arena results highlight fragmentation: MiniMax H3 variants and ByteDance Seedance 2.0 lead Elo scores for motion realism and native audio integration, while Kling 3.0 excels in character consistency and prompt adherence from stills. Google Veo 3.1 and Alibaba Wan models compete on photorealism and cost, Runway Gen-4.5 on editing controls, and Luma Ray on keyframe workflows. Rapid model iterations, benchmark volatility, and differing strengths across use cases—such as physics, lip-sync, or reference fidelity—keep consensus low. Key catalysts include potential new releases or updated leaderboards before month-end that could shift sentiment.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedAlibaba/Alibaba-ATH 27%
Runway 27%
SpaceXAI 26%
Luma AI 26%

Alibaba/Alibaba-ATH
27%

Runway
27%

SpaceXAI
26%

Luma AI
26%

26%

Shengshu
26%

Lightricks
26%

KlingAI
25%

Pika
25%

Pruna
25%

ByteDance
24%

Black Forest Labs
22%

Tencent
19%

MiniMax
18%

Pixverse
18%
Alibaba/Alibaba-ATH 27%
Runway 27%
SpaceXAI 26%
Luma AI 26%

Alibaba/Alibaba-ATH
27%

Runway
27%

SpaceXAI
26%

Luma AI
26%

26%

Shengshu
26%

Lightricks
26%

KlingAI
25%

Pika
25%

Pruna
25%

ByteDance
24%

Black Forest Labs
22%

Tencent
19%

MiniMax
18%

Pixverse
18%
Results from the "Rank" column under the "Image-to-Video Arena" Leaderboard tab at https://arena.ai/leaderboard/image-to-video filtered for "Models" will be used to resolve this market.
Note: Models marked “AutoEval” at the applicable check time will not be considered, regardless of whether they display a rank or score. Models marked “Preliminary” at the applicable check time will be considered.
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 Image-to-Video Arena 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: Sep 9, 2026, 3:52 PM ET
Resolver
0x69c47De9D...Results from the "Rank" column under the "Image-to-Video Arena" Leaderboard tab at https://arena.ai/leaderboard/image-to-video filtered for "Models" will be used to resolve this market.
Note: Models marked “AutoEval” at the applicable check time will not be considered, regardless of whether they display a rank or score. Models marked “Preliminary” at the applicable check time will be considered.
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 Image-to-Video Arena 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".
Resolver
0x69c47De9D...Traders see no dominant leader in image-to-video AI as the October deadline approaches, with market-implied odds clustered near 50% across most entrants. Recent Artificial Analysis arena results highlight fragmentation: MiniMax H3 variants and ByteDance Seedance 2.0 lead Elo scores for motion realism and native audio integration, while Kling 3.0 excels in character consistency and prompt adherence from stills. Google Veo 3.1 and Alibaba Wan models compete on photorealism and cost, Runway Gen-4.5 on editing controls, and Luma Ray on keyframe workflows. Rapid model iterations, benchmark volatility, and differing strengths across use cases—such as physics, lip-sync, or reference fidelity—keep consensus low. Key catalysts include potential new releases or updated leaderboards before month-end that could shift sentiment.
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