Note Manually translated and culturally adapted IFEval.

Note Manually translated and culturally adapted WinoGrande test set.

Note Manually annotated extractive question answering.

Note Manually annotated named entity recognition.

Note Machine-translated and post-edited choice of plausible alternatives.

Note Grammatical error correction. Text with errors → corrected text.

Note ERR news story transcripts generated by an ASR pipeline paired with the human written summary.

Note Newspaper article sentiment.

Note Trivia dataset extracted from the "Eesti Mäng" board game.

Note Exam questions on several subjects in multiple choice format.

Note Noun phrase inflection.

Note Extension of the MT-Bench dataset including Estonian, Livonian, Komi, and Võro.

Note Matching words with their dictionary definitions.

Note Multilingual extractive question answering with Wikipedia articles as context, includes Estonian. Questions are generated with Gemini-1.5-pro.

Note Machine-translated MMLU.

Note Machine-translated MMLU-Pro.

Note Multilingual machine-translated version of the `arc_challenge` dataset, includes Estonian.

Note Multilingual machine-translated version of the `gsm8k` dataset, includes Estonian.

Note Multilingual machine-translated version of the `truthfulqa` dataset, includes Estonian.

Note Multilingual machine-translated version of the `hellaswag` dataset, includes Estonian.

Note Multilingual machine-translated version of the `mmlu` dataset, includes Estonian.

Note Includes Estonian as one of the languages. English sources are translated to 200 languages. Any translation direction is possible potentially.

Note Machine-translated multilingual COPA. Includes validation and test for Estonian.

Note Includes English to Estonian translation direction.

Note Extension of the original Flores dataset adding additional translation directions, such as Estonian to Võro, Estonian to Komi-Zyrian, and some others.

Note Includes Estonian as one of the languages, classification labels remain in English.

Note Multiple choice reading comprehension. Includes Estonian as one of the languages.

Note Linguistic acceptability dataset derived from Universal Dependencies with heuristics. Includes Estonian as one of the languages.