AgentX: an open benchmark for million-token agentic inference
Source
SemiAnalysis
Author
SemiAnalysis
Date
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
subagent — A separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.
Why it matters
Hardware and serving comparisons built on single-turn 8k/1k traffic mislead for agentic workloads; this one models KV-cache reuse and subagentA separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.Full definition → bursts, and the dataset and dashboard are open.
articleNVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per WattElizabeth Goodman
articleAgenticCANNJunhao Qiu, Zidong Wang, Yansong Sun, Zhitong Ma, Ping Guo, Qingfu Zhang
articleHow NVIDIA Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context on NVIDIA Vera RubinTanya Lenz