Inception’s Mercury 2.5 reaches 770 output tokens per second, ranking near the top for LLM speed
EDITOR BRIEF
Artificial Analysis benchmarks show Mercury 2.5 delivering 770.4 output tokens per second, making it the second-fastest model in its comparison set. The proprietary text model has a 260k-token context window, moderate pricing, and below-average intelligence scores versus peer models.
INSIGHTS
Mercury 2.5 appears optimized for low-latency workloads where speed and cost matter more than frontier reasoning quality. Its profile reflects a growing split in the LLM market between high-intelligence models and fast, efficient models designed for production-scale applications.
COMMENTS
Discussion
> geekhaus:~$ next read?
Next read recommendations
phreak.ing
Phreak.ing publishes dial codes for an internet phone switch with calls, voicemail, intercom, paging, chat, and radio features
The Verge
The Social Reckoning is flopping at the box office
purplesyringa.moe