PulseAugur
EN
LIVE 22:22:40

Luma Labs releases new video model outperforming Google and OpenAI on reasoning

Luma Labs has released a new video generation model, luma/uni-1, which they claim outperforms Google's Nano Banana 2 and GPT-Image-1.5 on reasoning benchmarks. The model was developed with a "reasoning first, pixels second" approach and was used to create a football-themed video, inspired by the World Cup. These new models are now available via the AI/ML API. AI

IMPACT Sets a new benchmark for video generation models, potentially influencing future development in reasoning-first approaches.

RANK_REASON New model release from a notable AI lab. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on X — Luma Labs (video gen) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Luma Labs releases new video model outperforming Google and OpenAI on reasoning

COVERAGE [1]

  1. X — Luma Labs (video gen) TIER_1 English(EN) · LumaLabsAI ·

    RT @aimlapi: Yup, a football video. The World Cup made us do it

    RT @aimlapi: Yup, a football video. The World Cup made us do it Luma rebuilt image generation from scratch — reasoning first, pixels sec…