{"rewrite":{"id":"r_88a9a897747bc2ddb903af0f","clusterId":"c_62f3022a17f905360aad8f4c","slug":"minimax-h3-video-ai-ranks-second-in-blind-test-open-weights-coming","model":"deepseek-v4-flash:free","headline":"MiniMax H3 Video AI Ranks Second in Blind Test, Open Weights Coming","summary":"Chinese AI firm MiniMax announced MiniMax H3, a video generation model that creates up to 15 seconds of audio-synced video from text, images, or voice. It supports 768p or 2K resolution and accepts multiple media inputs at once. In a blind test by Artificial Analysis, H3 ranked second for text-to-video, behind Gemini Omni Flash and ahead of Seedance 2.0. The model is available via API now, with open weights planned soon.","whyItMatters":"MiniMax H3's second-place blind ranking and upcoming open-weight release position it as a strong open alternative in a field dominated by closed models.","webCardHtml":"\u003cp\u003eMiniMax, the Chinese AI company behind the open-weight M3 language model, has unveiled its latest video generator. MiniMax H3 accepts text, video, image, and audio inputs, and can combine several media types in a single prompt. It generates clips up to 15 seconds long at 768p or 2K resolution.\u003c/p\u003e\u003cp\u003eIndependent testing firm Artificial Analysis ran a blind comparison where models generated videos from identical prompts without names attached. For text-to-video with audio, H3 placed second, trailing Gemini Omni Flash but ahead of Seedance 2.0. For image-to-video with audio, H3 took third behind Seedance 2.0 and Gemini Omni Flash.\u003c/p\u003e\u003cp\u003eThe model is already usable through MiniMax\u0026#39;s API, and third-party tools like ComfyUI can call it. MiniMax says the model itself will be released as open weights in the near future.\u003c/p\u003e","blueskyPost":"MiniMax H3 video AI ranks 2nd in blind text-to-video test, behind Gemini Omni Flash and ahead of Seedance 2.0. Open weights coming soon. API live now.","twitterPost":"MiniMax H3 video AI: 15s clips, multi-modal input, 2nd in blind text-to-video test. Open weights planned. API available now.","threadsPost":null,"newsletterBlurb":"MiniMax announced H3, a video generation model that creates up to 15-second clips with audio from text, images, or voice. In a blind test by Artificial Analysis, it ranked second for text-to-video, behind Gemini Omni Flash and ahead of Seedance 2.0. The model is available via API now, with open weights planned soon.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260803-minimax-h3-video-generation-ai/\",\"title\":\"動画生成AI「MiniMax H3」が登場、世界2位の実力でオープンモデルとして公開予定\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5071,"outputTokens":634,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1786299710,"createdAt":"2026-08-09T18:03:34.000Z","publishedAt":"2026-08-09T18:06:45.000Z","updatedAt":"2026-08-09T18:03:34.000Z"},"cluster":{"id":"c_62f3022a17f905360aad8f4c","canonicalTitle":"動画生成AI「MiniMax H3」が登場、世界2位の実力でオープンモデルとして公開予定","representativeArticleId":"a_c3a08a18eab998acd72cb1bf","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"MiniMax H3\"],\"studios\":[\"MiniMax\"],\"people\":[],\"type\":\"announcement\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-08-03T01:56:00.000Z","lastSeenAt":"2026-08-03T01:56:00.000Z","updatedAt":"2026-08-09T18:06:45.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260803-minimax-h3-video-generation-ai/","title":"動画生成AI「MiniMax H3」が登場、世界2位の実力でオープンモデルとして公開予定"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["MiniMax H3"],"studios":["MiniMax"],"people":[],"type":"announcement","domain":"other","is_roundup":false},"keyFacts":null}