モデル ランキング

タスク横断の総合（マルチモーダル／ビジョン／言語など。サンプルデータ）。

Cross-task overview; multimodal, vision, and language may split into additional columns or child boards once eval JSON is wired.

更新: 2026-04-03

Public ranking policy: rows are sorted by composite score (desc). Composite score is a weighted sum of normalized sub-metrics; ties are broken by higher recent activity.