fal Releases H3 Max, a Post-Trained MiniMax H3 Video Model Claiming #1 Benchmark Ranks
- fal released H3 Max, a text-to-video and image-to-video model post-trained from the open-weights MiniMax H3 model and available through its API, Playground, and Agent.
- fal says H3 Max generates a five-second video in about three seconds, claiming roughly 35x the throughput of MiniMax's official H3 endpoint and 15x faster average generation than similarly rated models in its tests.
- Design Arena ranks H3 Max first on its recent image-to-video leaderboard at 1,341 Elo, ahead of official MiniMax H3 at 1,333, according to the press release.
- Artificial Analysis ranks fal's H3 model first on its Image-to-Video Leaderboard with Audio, scoring 1,201 Elo across 2,177 samples, the release says.
- fal trained H3 Max with substantial new data and an in-house reinforcement learning framework, then co-designed inference optimizations with the evolving model while retaining only changes that preserved quality gains.