Databricks tops Kimi K3 (max) benchmark with 218.8 t/s and 10.31s latency

mrdrozdov · x · 2026-08-04

Key findings

Artificial Analysis benchmarked 10 API providers for Kimi K3 (max) across output speed, time to first token, and blended price.

The report says provider choice materially changes performance, with a 637% spread between the fastest and slowest providers.

Original post →

More from Infra

Infra channel →