Intel announced an achievement in AI compute performance with its Intel Core Ultra Series 2 processors, becoming the first and only company to achieve full neural processing unit support in the newly released MLPerf Client v0.6 benchmark. This milestone marks the industry's first standardized evaluation of large language model performance on client NPUs.

Fastest NPU Response Time: Intel achieved the fastest NPU response time, generating the first word in just 1.09 seconds (first token latency), enabling near-instantaneous AI interaction.
Highest NPU Throughput: With a throughput of 18.55 tokens per second, Intel's NPU demonstrates superior efficiency in generating text, ensuring seamless real-time AI experiences.
Leading GPU Performance: Intel's built-in Intel Arc GPU showcased leadership in time to first token, reinforcing its end-to-end AI acceleration advantage.





