{"slug": "inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second", "title": "Inception Releases Mercury 3 Diffusion LLM at 1,068 Tokens per Second", "summary": "Inception released Mercury 3, a diffusion LLM that the company says runs at 1,068 tokens per second with a 1M-token context window. On Inception's own comparison table, Mercury 3 leads GPT-6 Luna and Claude Haiku 5.5 on 8 of 12 benchmarks.", "body_md": "Inception released Mercury 3, a diffusion LLM it says runs at 1,068 tokens per second with a 1M-token context. On Inception’s own table it leads GPT-6 Luna and Claude Haiku 5.5 on 8 of 12 benchmarks.\n\nThe post [Inception Releases Mercury 3 Diffusion LLM at 1,068 Tokens per Second](https://www.marktechpost.com/2026/10/19/inception-mercury-3-diffusion-llm/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second", "canonical_source": "https://www.marktechpost.com/2026/10/19/inception-mercury-3-diffusion-llm/", "published_at": "2026-10-20 03:32:43+00:00", "updated_at": "2026-10-20 16:21:33.667814+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "generative-ai", "ai-research"], "entities": ["Inception", "Mercury 3", "GPT-6 Luna", "Claude Haiku 5.5"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second", "markdown": "https://wpnews.pro/news/inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second.md", "text": "https://wpnews.pro/news/inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second.txt", "jsonld": "https://wpnews.pro/news/inception-releases-mercury-3-diffusion-llm-at-1068-tokens-per-second.jsonld"}}