spb/llmindex Public

The discriminative, contamination-resistant, fully transparent LLM ranking — updated live.

TypeScript 77.9% TeX 15.2% Python 3.7% SQL 1.4% JavaScript 1.1% Shell 0.5%

320 B

View source Raw Blame History

# data/runs

Run manifests and fit input/output JSON (hashes, matrices, fitted parameters) written by pnpm index:refit. Payloads (raw responses) live in the database — these files are the psychometric handoff between the TS worker and apps/psychometrics/fit.py.

Not committed (see .gitignore) except this README.