LetTokenBurn
Sign in
Incomplete14%Harbor nativeCoding

swe-marathon

Ultra long-horizon software engineering tasks from SWE-Marathon.

Homepage

How to run

ltb · swe-marathon
$ npm i -g lettokenburn-cli
$ ltb bench run abundant/swe-marathon@2 --benchmark swe-marathon -a claude-code -m anthropic/claude-opus-4-8
$ ltb bench push

Harbor-native: you can also call Harbor directly.

harbor
$ harbor run -d abundant/swe-marathon@2 -a claude-code -m anthropic/claude-opus-4-8

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

0 sourced entries

No sourced scores recorded yet.

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

abundant/swe-marathon