AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Seedream 3.0

ByteDance·

Imageimagecloud

Overview

ByteDance's bilingual (Chinese/English) text-to-image foundation model. Native 2048×2048 output with fast inference (~3s for a 1K image on an A100). Available via the Doubao and Jimeng apps.

Capabilities and innovations

Text-to-ImageBilingual (Chinese/English) promptsNative 2048×2048 outputFast inference (~3s at 1K)Bilingual text-to-image foundation modelNative 2K output

Benchmarks

No benchmark values are recorded for this model.

  • 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: benchmark did not exist at release

Links

    More from ByteDance

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