MiniMax's H3 and post-trained H3 Max variants currently lead Artificial Analysis image-to-video leaderboards with audio, posting top Elo scores above 1200 through superior prompt adherence, motion realism, native 2K output, and integrated stereo sound from single-frame inputs. This positioning stems from the model's July 2026 multimodal architecture, which supports omni-reference inputs and fast inference, plus recent fal optimizations that boosted throughput and aesthetics without sacrificing quality. Traders assign MiniMax an 80% implied probability because these verifiable benchmark results and commercial workflows have outpaced competitors like ByteDance Seedance, Google Gemini Omni Flash, and Kling 3.0 in head-to-head evaluations through early September. Resolution at month-end hinges on any final model updates or new arena data before the cutoff, though rapid iteration in the space leaves room for late shifts.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedMiniMax 80%
Google 12%
Luma AI 3.4%
Pixverse 3.3%

MiniMax
80%

12%

Luma AI
3%

Pixverse
3%

Black Forest Labs
3%

Pruna
2%

Alibaba/Alibaba-ATH
1%

ByteDance
1%

SpaceXAI
1%

KlingAI
1%

Lightricks
1%

Shengshu
1%

Tencent
1%

Pika
1%

Runway
<1%
MiniMax 80%
Google 12%
Luma AI 3.4%
Pixverse 3.3%

MiniMax
80%

12%

Luma AI
3%

Pixverse
3%

Black Forest Labs
3%

Pruna
2%

Alibaba/Alibaba-ATH
1%

ByteDance
1%

SpaceXAI
1%

KlingAI
1%

Lightricks
1%

Shengshu
1%

Tencent
1%

Pika
1%

Runway
<1%
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, 3:53 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...MiniMax's H3 and post-trained H3 Max variants currently lead Artificial Analysis image-to-video leaderboards with audio, posting top Elo scores above 1200 through superior prompt adherence, motion realism, native 2K output, and integrated stereo sound from single-frame inputs. This positioning stems from the model's July 2026 multimodal architecture, which supports omni-reference inputs and fast inference, plus recent fal optimizations that boosted throughput and aesthetics without sacrificing quality. Traders assign MiniMax an 80% implied probability because these verifiable benchmark results and commercial workflows have outpaced competitors like ByteDance Seedance, Google Gemini Omni Flash, and Kling 3.0 in head-to-head evaluations through early September. Resolution at month-end hinges on any final model updates or new arena data before the cutoff, though rapid iteration in the space leaves room for late shifts.
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