Inception Launches Mercury 3 Diffusion LLM Reaching 1,068 Tokens Per Second
Inception has released Mercury 3, a diffusion large language model boasting a blistering speed of 1,068 tokens per second and a one-million-token context window. According to the company's benchmarks, the new model outperforms competitors like GPT-6 Luna and Claude Haiku 5.5 across eight of twelve standard evaluations, marking a significant advancement in generative AI performance and efficiency.
Source: MarkTechPost