Following up on the Haskell benchmark, the OCaml benchmark, and the Python benchmark, I ran AoC 2025 Days 1–5 in ReScript — a typed functional language that compiles to JavaScript with a lean standard library, a distinct syntax, and very limited LLM training data.
This post covers three runs of the same benchmark, each adding a different intervention to see what helps models cope with an unfamiliar language:
- Run 1 — no help at all. 3-minute timeout. 1 completer out of 10.
- Run 2 — overflow warning + longer timeout. 2 completers.
- Run 3 — a ReScript system prompt teaching syntax, stdlib, and types. 7 completers.