AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Seedance 2.0

ByteDance·

Videomultimodalcloud

Overview

ByteDance text/image/audio-to-video model with unified audio-video joint generation. Generates 4-15s clips up to 1080p across multiple aspect ratios. Available via Volcano Engine and API.

Capabilities and innovations

Text-to-videoImage-to-videoAudio-video joint generationUp to 1080p output4-15s clipsUnified multimodal audio-video architectureMultimodal reference inputs (text/image/audio/video)Director-level camera & lighting control

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 ByteDance

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