Specialized beats general. Generalists spread thin across the entire internet. Lumen Outpost goes narrow on what production engineers actually ship — legacy languages, maintainable diffs, lower cost per task.
13 languages tested with the same pass@3 evaluation. Tap one.
We also post-train on COBOL, C++, C#, and JavaScript.
Enterprise workhorse. Lumen edges GPT-5.5 by 4.5 points and clears every other model by 10+.
Generalists spend theirs on the entire internet. We spent ours on the code your company actually runs.
Lumen is post-trained on ABAP, Fortran, COBOL, Verilog, Rust — and the production-engineering habits that make code maintainable on long-lived systems. Generalists treat these as a long-tail afterthought.
AI assistants love to add 'just in case' helpers, defensive checks for impossible states and config flags for hypothetical futures. Three months later your team is reading paragraphs of comments to explain a one-line change. Slop-Bench measures the difference between code that passes the test and code your engineers will still want to maintain in a year.
Penalised duplication, dead code and unnecessary complexity. Rewarded minimal diffs that match repo style.
Lumen leads on slop while every other model that scores well on code-quality benchmarks bloats its diffs to get there. Lumen's diffs are shorter, more focused, and align with your repo style.
One command. Mid-session model switching included.
cosine
Download for Mac
Linux