Mercury 3 is the most capable diffusion LLM released to date. It outperforms GPT-6 Luna and Claude Haiku 5.5 while running 4–8x faster at 1,000+ tokens per second.
Key takeaways
Mercury 3, a diffusion-based LLM, outperforms GPT-6 Luna and Claude Haiku 5.5 and runs at 1,000+ tokens per second.
- Mercury 3 is 40x larger and 3x more intelligent than Mercury 1.
- It matches or exceeds the performance of speed-optimized models like GPT-6 Luna.
- Mercury 3 is 50% off at launch with discounted cached tokens.
Summarised automatically by AI from the original article by Hacker News. AI can make mistakes, so check the original for details.
Today we’re introducing Mercury 3, the most capable diffusion-based LLM released to date. Across a range of benchmarks, Mercury 3 outperforms GPT-6 Luna and Claude Haiku 5.5, while running 4–8x faster at 1,000+ tokens per second.
Mercury 3 demonstrates that text diffusion scales. It’s more than 40x larger than Mercury 1 and is vastly more intelligent, but just as fast.
Quality: On par or better than frontier speed-optimized models like GPT-6 Luna and Claude Haiku 5.5.
At launch, Mercury 3 is 50% off at $0.10 per 1M input and $0.35 per 1M output. Cached tokens are 90% off the input price.
