Mercury 2.5

Latest news

1. 19 Oct
   Mercury 3: diffusion LLM claims frontier performance and 1,068 tok/s

   The Mercury team announced Mercury 3, a diffusion-based large language model they say outperforms GPT-6 Luna and Claude Haiku 5.5 on benchmarks while running 4–8× faster at over 1,000 tokens per second. The model supports a 1M-token context window, is ~40× larger than Mercury 1, and is offered with introductory pricing and discounts.

   Models · 1 source

   

Articles

No articles about Mercury 2.5 yet.