Mercury 3
Summary
Mercury 3 是目前发布的最强扩散式大语言模型，宣称以 1,000+ tokens/s 的速度运行，比竞争对手快 4–8 倍，并在性能上超越 GPT-6 Luna 和 Claude Haiku 5.5，实现 40 倍扩展而不降低速度。
View Cached Full Text
Cached at: 10/22/26, 07:38 PM
Similar Articles
Mercury 3 [Inception Labs] - Matching Luna/Haiku at 1000 tokens/sec
Inception Labs 发布 Mercury 3，这是迄今最强的扩散式 LLM，在多项基准上超越 GPT-6 Luna 和 Claude Haiku 5.5，同时以 1000+ tokens/秒的速度快 4-8 倍。模型规模比 Mercury 1 大 40 倍以上，支持 100 万 token 上下文，并以极具竞争力的价格面向生产环境开放。
Mercury 2.5
Inception Labs releases Mercury 2.5, a diffusion-based language model with improved intelligence, speed, and cost-efficiency for production use in search, voice, and coding.
@StefanoErmon: Today we're excited to announce Mercury 2.5 It’s the most capable diffusion LLM on the market. It is a 40% jump in inte…
Mercury 2.5 is announced as the most capable diffusion language model, with a 40% increase in intelligence over Mercury 2, operating at over 1,100 tokens/sec on NVIDIA GPUs, and optimized for production with low latency and cost.
Inception Labs' Mercury 2 AI Beats Google's DiffusionGemma at Its Own Game (4 minute read)
Inception Labs released Mercury 2, a diffusion language model that generates roughly 1,000 tokens per second and outperforms Google's DiffusionGemma on the AIME 2026 benchmark with a score of 90% versus 69.1%, though DiffusionGemma is free and open-weight while Mercury 2 is a paid, closed-weight API model.
@FeitengLi: Hy-MT2 - a new open-source multilingual translation model that matches top-tier large models in capability, supports translation between 33 languages, and offers flexible instruction capabilities. It achieves 2-bit quantization under 500MB, making it well-suited for on-device deployment. https://modelsc…
Hy-MT2 is a new open-source multilingual translation model from Tencent Hy that supports 33 languages, offers flexible instruction capabilities, and achieves 2-bit quantization under 500MB for on-device deployment.