lukekim/evals

Datasets

cube_pack__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/cube-pack/samples.jsonl

historical_kana_orthography_reading__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/historical-kana-orthography-reading/samples.jsonl

canto_wu_pronunciation_fewshot__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/canto_wu_pronunciation/samples_few.jsonl

accounting_audit__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/accounting_audit/samples.jsonl

brazilian_lexicon__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/brazilian-lexicon/samples.jsonl

naughty_strings__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/naughty_strings/samples.jsonl

korean_phonetics__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/korean-phonetics/samples.jsonl

chinese_homophonic__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_homophonic/chinese_homophonic.jsonl

count_intersections_polynomial__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/count_intersections_polynomial/samples.jsonl

coqa_match__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/coqa/match.jsonl

latin_grammar__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/latin_grammar/samples.jsonl

bitwise__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/bitwise/samples.jsonl

shared_borders__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/shared_border/samples.jsonl

japanese_station__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/japanese-station/samples.jsonl

atpl_exams__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/atpl_exams/samples.jsonl

invoice_due_date_leap_day_adjustment__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/invoice_due_date_leap_day_adjustment/samples.jsonl

romanian_homonyms__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/romanian_homonyms/samples.jsonl

infiniteloop_match__s1__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/infiniteloop-match/infiniteloop-match.jsonl

russian_nlp_tasks__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/russian-nlp-tasks/samples.jsonl

chinese_chu_ci__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_chu_ci/samples.jsonl

polish_syllable_count__val__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/polish-syllable-count/samples.jsonl

korean_postposition__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/korean-postposition/samples.jsonl

bulgarian_lexicon__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/bulgarian-lexicon/samples.jsonl

compare_countries_area__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/compare-countries-area/samples.jsonl

pattern_identification__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/pattern_identification/samples.v0.jsonl

belarusian_synonyms__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/belarusian_synonyms/samples.jsonl

spanish_feminine_noun_masculine_article__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/spanish_feminine_noun_masculine_article/samples.jsonl

sarcasm__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/sarcasm/samples.jsonl

chinese_tang_poetries__dev__match_v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_tang_poetries/sample.jsonl

japanese_number_reading__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/japanese_number_reading/japanese_number_reading.jsonl

korean_honorific__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/korean-honorific/samples.jsonl

complex_replace_characters__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/complex_replace_characters/samples.jsonl

dice_rotation_sequence__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/dice-rotation-sequence/samples.jsonl

utah_real_estate__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/utah_real_estate/samples.jsonl

formal_logic__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/formal_logic/formal_logic_expressions.jsonl

resistor_ohm_calculator__dev__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/resistor_ohm_calculator/samples.jsonl

gol__dev__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/GOL/samples.jsonl

icelandic_sentences_gec__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/icelandic-sentences-gec/samples.jsonl

chinese_modern_poem_identification__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_modern_poem_identification/samples.jsonl

reverse_string__s1__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/reverse_string/reverse_string.jsonl

complex_analogies_en_ru__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/complex-analogies-en-ru/samples.jsonl

positive_binary_operations__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/positive-binary-operations/samples.jsonl

hindi_shuddha__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/hindi_shuddha/samples.jsonl

tokyo_station_number__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/tokyo-station-number/samples.jsonl

chinese_famous_novel__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_famous_novel/samples.jsonl

diagrammatic_logic__dev__v2

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/diagrammatic_logic/samples.jsonl

polish_lexicon__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/polish-lexicon/samples.jsonl

wkt_understanding__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/wkt_understanding/samples.jsonl

japanese_national_medical_exam02__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/japanese-national-medical-exam02/japanese-national-medical-exam02.jsonl

cardinal_directions__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/cardinal-directions/samples.jsonl

rectangles__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/rectangles/samples.jsonl

hindi_upsc__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/hindi_upsc/samples.jsonl

three_pt_mapping__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/three-pt-mapping/three_pt_mapping.jsonl

polish_proverbs__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/polish-proverbs/samples.jsonl

indonesian_numbers__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/indonesian_numbers/indonesian_numbers.jsonl

chinese_song_ci__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_song_ci/samples.jsonl

cybersecurity_filepaths__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/cybersecurity/filepaths.jsonl

taxes__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/taxes/samples.jsonl

crontab__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/crontab/samples.jsonl

integer_sequence_predictions_misc__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/integer-sequence-predictions/misc-and-recent-sequences.jsonl

integer_sequence_predictions_obscure__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/integer-sequence-predictions/obscure-sequences.jsonl

integer_sequence_predictions_notable__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/integer-sequence-predictions/notable-sequences.jsonl

integer_sequence_predictions__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/integer-sequence-predictions/samples.jsonl

belarusian_orthography__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/belarusian_orthography/samples.jsonl

date_booking__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/date-booking/samples.jsonl

interlingual_homograph__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/interlingual-homograph/samples.jsonl

stats_tests__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stats-tests/samples.jsonl

belarusian_russian_translation__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/belarusian_russian_translation/samples.jsonl

date_calculator__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/date-calculator/samples.jsonl

chinese_poem__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/chinese_poem/samples.jsonl

belarusian_lexicon__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/belarusian_lexicon/samples.jsonl

test_english_pronunciations__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/test_english_pronunciations/samples.jsonl

anagrams__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/anagrams/samples.jsonl

guess_the_singer__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/guess_the_singer/samples.jsonl

illinois_law__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/illinois-law/samples.jsonl

russian_medical__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/russian_medical/samples.jsonl

bigrams__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/bigrams/samples.jsonl

probability_questions__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/probability_questions/probability_questions.jsonl

vintage_phone_keyboard_decode__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/vintage_phone_keyboard_decode/samples.jsonl

connect4__s1__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/connect4/samples.jsonl

stock_options_bull_call_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_options_bull_call_spread.jsonl

stock_options_bear_call_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_options_bear_call_spread.jsonl

stock_option_terms_bear_call_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_option_terms_bear_call_spread.jsonl

stock_option_terms_iron_butterfly_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_option_terms_iron_butterfly_spread.jsonl

stock_option_terms_bull_call_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_option_terms_bull_call_spread.jsonl

stock_options_inverse_iron_condor_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_options_inverse_iron_condor_spread.jsonl

stock_options_iron_condor_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_options_iron_condor_spread.jsonl

stock_option_terms_iron_condor_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_option_terms_iron_condor_spread.jsonl

stock_options_inverse_iron_butterfly_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_options_inverse_iron_butterfly_spread.jsonl

stock_option_terms_inverse_iron_condor_spread__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/stock_options/stock_option_terms_inverse_iron_condor_spread.jsonl

japanese_romantic_context__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/japanese_romantic_context/samples.jsonl

phonetics_identify_words_needing_missing_gpcs__s1__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/phonetics-identify-words-needing-missing-gpcs/samples.jsonl

prompt_injection__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/prompt-injection/samples.jsonl

word_vector_over_reliance__dev__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/word_vector_over_reliance/word_vector_over_reliance_samples.jsonl

iso_to_lunar_calendar__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/lunar_calendar/iso_to_lunar_calendar.jsonl

lunar_calendar_to_iso__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/lunar_calendar/lunar_calendar_to_iso.jsonl

code_combination__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/code_combination/samples.jsonl

partially_solved_crossword_clues__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/partially_solved_crossword_clues/samples.jsonl

quartz__test__v1

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/quartz/samples.jsonl

physics__interaction__dev__v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/physics-interaction/samples.jsonl

next_val_series__dev__simple_v0

https://github.com/Jeadie/evals/raw/refs/heads/main/evals/registry/data/next-val-series/next-val-series.jsonl