Kimi K3 tested on a Rust optimization task: one-shot success and a 2% speedup

Tested Kimi K3 for Coding

The author asked Kimi K3 to optimize a hand-tuned Rust function. The model chose a SWAR approach, treating a 64-bit value as eight u8 values, completed the task in about 15 minutes with zero errors, and delivered a 2% speedup. Token cost was roughly $1 via OpenRouter. The author sees this as near-frontier performance.

Why it matters: A clean first-person experiment: the author threw a hand-tuned Rust function at Kimi K3, the model chose SWAR on its own, delivered zero-error code in 15 minutes, and netted a 2% speedup for ~$1. High signal density with concrete numbers and approach names—not marketing fluff....