AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

FLUX 3

Black Forest Labs·

Videomultimodalcloud

Overview

Unified multimodal flow model that generates image, video and audio from a single backbone and can be extended to predict robot actions. Rollout was staged: FLUX 3 Video with native synchronised audio (clips up to 20 seconds, aspect ratios from 9:16 to 21:9) and the action model launched in application-based early access, with image generation and an open-weight FLUX 3 Dev backbone announced for later. No public API tier, pricing, parameter count or benchmark methodology published at launch. The open releases have since arrived as separate models rather than as one Dev backbone: FLUX 3 Action (7B robot policy, 2026-09-23) and FLUX 3 Image Klein (5.6B image model, 2026-10-15). FLUX 3 Video now ranks #2 in the Text-to-Video Arena at ~1,496 Elo, behind Gemini Omni Flash (~1,512) and ahead of Dreamina Seedance 2.0 (~1,478) — the first independent quality signal for the model.

Capabilities and innovations

Text-to-video (up to 20s)Native synchronised audioImage-to-videoVideo-to-video from reference clipKeyframe-to-video transitionsRobot action predictionSingle flow backbone for image, video, audio and actionVideo and native audio generated jointlyText-to-Video Arena #2 at intake (~1,496 Elo)

Benchmarks

No tracked academic benchmark applies to video models; the timeline carries no scores and no leadership tracking for them.

  • GPQA Diamond: not reported by the vendor
  • Humanity’s Last Exam (no tools): not reported by the vendor
  • SWE-bench Verified: not reported by the vendor
  • SWE-bench Pro: not reported by the vendor
  • MMLU: not reported by the vendor
  • MMLU-Pro: not reported by the vendor
  • Terminal-Bench 2.x: not reported by the vendor
  • MMMU-Pro: not reported by the vendor

Links

More from Black Forest Labs

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.