Model Accuracy

Passive quality ranking from cache displacement Elo + neighborhood scoring. Zero extra API cost.

Loading...

Elo Leaderboard

# Model Elo ▼ W L Success Queries Latency Categories
⟳ Loading...

Complexity Radar

Category Heatmap

Recent Displacements

⟳ Loading...

Neighborhood Explorer

Shows which models perform best for queries similar to yours.