LetTokenBurnSWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
$ npm i -g lettokenburn-cli$ ltb bench info swe-perf
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
No sourced scores recorded yet.
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
Paper | Code | Project Page
Dataset Summary
Optimizing code performance is paramount in software engineering, yet it remains a largely unexplored frontier for Large Language Models (LLMs). While models excel at fixing bugs, their ability to make code faster at a repository-scale is not well understood. To address this, we introduce SWE-Perf, the first benchmark meticulously designed to…