Seed1.5-VL

Training compute

1.4×10²⁴ FLOP

Published

May 11, 2025

Seed1.5-VL is an AI model developed by ByteDance (China), first published in May 2025. It works in the vision, language, multimodal and video domain, on tasks such as visual question answering, video description, language modeling/generation and 2 more.

Training it took an estimated 1.4×10²⁴ FLOP of compute (estimation method: hardware). It was trained on roughly 3T datapoints. Training ran on NVIDIA H800 SXM5.

Access: API access. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: ByteDance
Country of organization: China
Domain: Vision, Language, Multimodal, Video
Task: Visual question answering, Video description, Language modeling/generation, Question answering, Character recognition (OCR)
Training compute: 1.4×10²⁴ FLOP
Compute estimation method: Hardware
Dataset size: 3T
Training hardware: NVIDIA H800 SXM5
Chip-hours: 1.3M
Model accessibility: API access
Open weights: No
Epoch confidence: Confident