Seed 1.5-VL vs Seed-1.8

ByteDance

Seed1.5-VL, released by ByteDance Seed on May 15, 2025, is a vision-language foundation model composed of a 532M-parameter vision encoder and a Mixture-of-Experts language model with 20 billion active parameters. It was pretrained on over 3 trillion multimodal tokens and achieved state-of-the-art performance on 38 out of 60 public VLM benchmarks at release. Seed1.5-VL targets complex visual reasoning, OCR, video comprehension, 3D spatial understanding, and multimodal agentic tasks.

ByteDance

Seed-1.8, developed by ByteDance Seed, is a generalized agentic large language model supporting text and image input, with industry-leading GUI agent capabilities and improvements in multimodal reasoning over its predecessor Seed1.5-VL. It targets information retrieval, code generation, GUI interaction, and complex agentic workflows requiring robust multimodal understanding.