Upload from GitHub Actions: flores filter for available dev split

Upload from GitHub Actions: improve norwegian fix

Upload from GitHub Actions: fix norwegian

Upload from GitHub Actions: Merge pull request #22 from datenlabor-bmz/dev

Upload from GitHub Actions: Add auto-translated datasets

Upload from GitHub Actions: Merge pull request #18 from datenlabor-bmz/pr-17

Upload from GitHub Actions: Add auto-translated datasets

Upload from GitHub Actions: updated and cleaned up scripts for new eval runs

Upload from GitHub Actions: Add Todos for using existing machine-translated datasets rather than our own ones

Upload from GitHub Actions: updated translation functions

Upload from GitHub Actions: updated frontend and backend to fix bugs

Upload from GitHub Actions: Merge pull request #9 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: TruthfulQA translation WIP

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

Upload from GitHub Actions: Translate MMLU and evaluate

Upload from GitHub Actions: Correlation plot

Upload from GitHub Actions: Evaluate on autotranslated GSM dataset

Upload from GitHub Actions: Add math benchmarks

Upload from GitHub Actions: Use FLORES+ via Huggingface

Upload from GitHub Actions: Fix vibecoding

Pass through kwargs

Fix dataset loading

Fix import paths

added download function and edited INFO

Only run tasks for which there is no result yet

Run on 40 languages, additional models

Move functions for sharing them

Implement MMLU task

MMLU data loader for 3 parallel datasets

Analyze MMLU datasets

Refactor eval code into files