Add various difficulty evals and a UI for comparison#5

Merged

andrewginns merged 15 commits intomainfrom

add-levels-of-eval-difficulty

Jun 9, 2025

Commits on Jun 4, 2025

chore: Bump model versions
andrewginns
committed
feat: Simplified python wrapper for MCP server over the npx mermaid validator
andrewginns
committed
Merge remote-tracking branch 'origin/main' into add-levels-of-eval-difficulty
andrewginns
committed

Commits on Jun 7, 2025