Mercury 3 is a diffusion LLM that hits 1,068 tokens/s. See how it differs from autoregressive models and how it compares with Haiku 5.5 and GPT-6 Luna.
diffusion LLMMercury 3 benchmarksMercury 3 vs Claude Haiku 5.5
Mercury Decide returns an answer and probability in about 0.16 seconds, now with images. How it works, its independent evals, and how to pair it with Mercury 3.
