PrunaAI's video model ranks #2-6 on DesignArena human preference benchmarks, runs in seconds
kiankatan · x · 2026-09-29
PrunaAI announced its video model now runs in seconds and ranks #2-6 on independent DesignArena benchmarks for human preference. The team credits post-training and model optimization, built on MiniMax's open-source H3 work, and says scaling efforts are just beginning.
Related event: PrunaAI's P-Video-2 Pro ranks second in image-to-video arena(3 posts)→
More from Multimodal
- Eleven v4 tested with the author's own voice, nearly removing her accent — ciguleva · 2026-09-29
- ElevenLabs launches Eleven v4, its fastest and most emotive AI voice model yet — Polymarket · 2026-09-29
- Physics-simulated instruments played by an LLM: full rehearsal finally succeeds — alexanderchen · 2026-09-29
- AI video tip: import a movie scene's camera move, replace everything else — LearnWithBishal · 2026-09-29
- Villain-boss POV video made with Magnific and Seedance 2.5, prompt shared — charis_ai · 2026-09-29
- Ask HN-adjacent: local faceswap workflows all broken after reinstall — DwemerNose · 2026-09-29