Upload from GitHub Actions: Get more results, compute average based on all tasks

Upload from GitHub Actions: Correlation plot

Upload from GitHub Actions: Fix linter problems in frontend

Upload from GitHub Actions: More models and languages

Upload from GitHub Actions: Improve UX and style

Upload from GitHub Actions: Improve UX and style

Upload from GitHub Actions: Merge remote changes with local frontend updates

Upload from GitHub Actions: Merge remote changes and apply terminology updates: Commercial->closed-source, Open->open-source

Upload from GitHub Actions: Use task subset for average score

Upload from GitHub Actions: Eavaluate on 40 languages

Upload from GitHub Actions: Add math benchmarks

Upload from GitHub Actions: Quick fixes

Upload from GitHub Actions: Display N/A scores as such

Add symbols for progress plot

Display more language names

Run on 40 languages, additional models

Add scores to world map hover title

Fix response when no evals data is available

Remove unnecessary function

Fix: sort copy, not in place

Improve plots and dataset table

Add model history plot

Add nice cumulative language population plot

Implement MMLU task

Add dataset metadata about human/machine translation

Refactor score columns

Translation both from and to

Add OpenRouter metadata to models

Run on 100 languages, adjust display

Dataset table grouping

Adjust font sizes

Add Dockerfile

Fix world map and apply filters for it

AutoComplete improvements and examples

Speed things up

Language selection checkboxes & filtering in backend

Basic backend setup with FastApi but without actual filtering

Store filter state globally

Plot carousel

Better map tooltip

Chloropleth map based on NaturalEarth

Simple Plot map

D3 map with countries (without data display)

Autonymns and cooler dataset search display

Search field

Minor table formatting

Nicer layout for datasets table and other tables

Colourful boxes

Datasets table

Basic language table