Last updated:
This page defines production scoring standards; published scores must remain consistent with the same documentation.
All site lists are rankable and auditable. The formulas below are publicly documented in both UI and source code.
Sort order: composite score descending.
Composite score: normalize each sub-metric with min-max, then compute a weighted sum. Ties are broken by higher recent activity (e.g., commits in the last 30 days).
Within-group formula: Score = 100 × [0.30·Stars + 0.15·Forks + 0.30·Commits30d + 0.15·Contributors + 0.05·(1-Issues) + 0.05·(1-PRs)].
All terms are min-max normalized within the same group; Issues/PR are inverse signals (lower is better).
Four boards map to Models, Agents, LLMs, and Toolchains; columns may extend independently (vendor, domain, size, coverage, etc.).
Composite scores use configurable weights and normalization; multi-benchmark setups must declare benchmark versions, weights, and missing-value handling.
Static builds: commit JSON or fetched artifacts, then run SSG.
Scheduled jobs: GitHub Actions may run evaluators or aggregators, write artifacts, and trigger builds; read-only edge storage must be weighed against static-first goals.
The Sources page should list primary sources, fetch times, and versions; caching or sampling must be disclosed. Readers may cross-check Methodology against Sources.
Common issues include benchmark leakage, overfitting to public eval sets, vendor-reported scores vs. independent reproduction, and composite scores masking weak tasks. Mitigations: pin task versions, publish seeds and scripts, disclose per-task scores, and review third-party leaderboard changelogs.
GitHub momentum is gameable—cross-check stars with commits, issues/PRs, and release cadence.
