Alibaba HappyHorse participates in Arena blind testing for the first time and tops the video editing track; the official version will be released in two weeks.

ME News report. On April 15 (UTC+8), according to Beating Monitoring, Alibaba’s ATH AI Innovation Department’s AI video model HappyHorse announced that version 1.0 has launched on UC Berkeley’s community blind testing platform Arena (formerly LMArena). In its first competition, it scored 1299 points (preliminary score, ±21) to take first place in the video editing (Video Edit) category, ahead of the second-place xAI grok-imagine-video by 42 points and ahead of the third-place Kuaishou KeLing o3-pro by 48 points. HappyHorse previously topped the rankings on another evaluation platform, Artificial Analysis, in the text-to-video and image-to-video lists, and video editing is its newly expanded track. Arena officials say that video editing is an emerging frontier capability of video models, and currently only a few models support it. The HappyHorse team said it is currently in the final optimization sprint ahead of the official release, which will launch in two weeks. Community users can now preview and vote on it in advance at arena.ai. (Source: BlockBeats)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin