AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Seedance 1.0

ByteDance·

Videomultimodalcloud

Overview

ByteDance's first Seedance video-generation model, introduced at the Volcano Engine Force conference. Fast text- and image-to-video generation with multi-shot narrative sequences.

Capabilities and innovations

Text-to-videoImage-to-videoMulti-shot narrativesFast generationMulti-shot narrative video generationFirst Seedance video model

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: benchmark did not exist at release
  • MMMU-Pro: not reported by the vendor

Links

    More from ByteDance

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