Composite builder
Build your own transparent AI model ranking.
Start from a use case like coding copilot or cheap but strong, then tune the benchmark weights without hiding how the score is built.
Scenario presets
Start from a named scenario first, then keep editing the formula if you want a custom mix.
score = 0.44 × Code Arena + 0.32 × Reasoning + 0.24 × Long Context ReasoningEach ingredient is normalized inside its benchmark group first. The formula is the product.
Ingredients
Adjust the weights. The ranking updates instantly below.
29
21
16