SPB Git

spb/llmindex Public

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

webappaillmbenchmark
TypeScript 77.9% TeX 15.2% Python 3.7% SQL 1.4% JavaScript 1.1% Shell 0.5%
320 B · 8 lines markdown
Rendered Raw Blame History 
1# data/runs23Run manifests and fit input/output JSON (hashes, matrices, fitted parameters) written by4`pnpm index:refit`. Payloads (raw responses) live in the database — these files are the5psychometric handoff between the TS worker and `apps/psychometrics/fit.py`.67Not committed (see .gitignore) except this README.8