chore: update data with agentic results

fix(docs): update docs on mutations

feat: include tag in experiment ID

refactor: migrate to integrate with inspect evals

feat: update sample-wise comparison with detailed emoji legend

feat: add support for filtering by invalid JSON in leaderboard

feat: sample-wise comparison

feat: add tabs for metrics and variants information

feat: a simple leaderboard with filtering

Duplicate from gradio-templates/leaderboard