How DistilCode saves tokens

DistilCodeBack to home

How they are saved

We apply 14 optimisations on your context, to reduce your input tokens. Optimisations keep your context history byte identical so your cache isn't broken. Each one is listed on this page:
Keeping up with AI is a job itself. As new models arrive, we research the best and most efficient way to use them, then fold that into our harness—so you only have to worry about getting your work done.

How they were evaluated

Built to mirror real work.

  • AgencyBench V2

    Evaluated on AgencyBench V2—long, multi-subtask agentic work rather than single isolated issues.
  • Multi-subtask runs

    Each run chains several dependent subtasks, so early decisions and context carry into later ones.
  • Built to fill the 1M context window

    Runs are designed to consume the whole 1M-token context window, where wasted tokens hurt the most.
  • Real agentic work

    Models worked the way they would in practice—in a live repository.
  • Same LLMs, two harnesses

    Identical models faced the same problems: one on a conventional agentic loop (opencode) and one on our harness.
  • What we measured

    Cost, tokens used and correct answers, compared run for run: 66% lower cost, 80% fewer tokens and 18% more correct answers.

The benchmark, including the detailed methodology and results, has been published at github.com/DistilCode/distilcode-study.

Download DistilCode