LICENSE
MANIFEST.in
README.md
pyproject.toml
evals/__init__.py
evals/api.py
evals/base.py
evals/data.py
evals/eval.py
evals/formatting.py
evals/metrics.py
evals/record.py
evals/registry.py
evals/registry_test.py
evals/cli/oaieval.py
evals/cli/oaievalset.py
evals/completion_fns/__init__.py
evals/completion_fns/cot.py
evals/completion_fns/langchain_llm.py
evals/completion_fns/langchain_math.py
evals/completion_fns/openai.py
evals/completion_fns/retrieval.py
evals/elsuite/lambada.py
evals/elsuite/multiple_choice.py
evals/elsuite/translate.py
evals/elsuite/utils.py
evals/elsuite/utils_test.py
evals/elsuite/basic/fuzzy_match.py
evals/elsuite/basic/fuzzy_match_test.py
evals/elsuite/basic/includes.py
evals/elsuite/basic/includes_test.py
evals/elsuite/basic/json_validator.py
evals/elsuite/basic/json_validator_test.py
evals/elsuite/basic/match.py
evals/elsuite/basic/match_test.py
evals/elsuite/modelgraded/base.py
evals/elsuite/modelgraded/classify.py
evals/elsuite/modelgraded/classify_utils.py
evals/elsuite/test/match.py
evals/prompt/base.py
evals/registry/completion_fns/cot.yaml
evals/registry/completion_fns/langchain_chains.yaml
evals/registry/completion_fns/langchain_llms.yaml
evals/registry/eval_sets/coqa-ex.yaml
evals/registry/eval_sets/logiqa-logical-reasoning-plus.yaml
evals/registry/eval_sets/manga-translation.yaml
evals/registry/eval_sets/mazes.yaml
evals/registry/eval_sets/pointer-value-retrieval.yaml
evals/registry/eval_sets/raven-matrices.yaml
evals/registry/eval_sets/stock-options.yaml
evals/registry/eval_sets/test-all.yaml
evals/registry/eval_sets/test-basic.yaml
evals/registry/eval_sets/test-modelgraded.yaml
evals/registry/eval_sets/ukraine-gec.yaml
evals/registry/evals/2d_movement.yaml
evals/registry/evals/3d_globe_movement.yaml
evals/registry/evals/Unfamiliar-Chinese-Character.yaml
evals/registry/evals/aba-mrpc-true-false.yaml
evals/registry/evals/abstract-causal-reasoning.yaml
evals/registry/evals/actors-sequence.yaml
evals/registry/evals/adultery_state_laws.yaml
evals/registry/evals/afrikaans-lexicon.yaml
evals/registry/evals/aime_evaluation.yaml
evals/registry/evals/algebra-word-problems.yaml
evals/registry/evals/allergen-information.yaml
evals/registry/evals/alternate-numeral-systems.yaml
evals/registry/evals/ambiguous-sentences.yaml
evals/registry/evals/anagrams.yaml
evals/registry/evals/arc.yaml
evals/registry/evals/arithmetical_puzzles.yaml
evals/registry/evals/ascii-digit-recognition.yaml
evals/registry/evals/ascii-wordart.yaml
evals/registry/evals/asl-classifiers.yaml
evals/registry/evals/atpl_exams.yaml
evals/registry/evals/balance-chemical-equation.yaml
evals/registry/evals/banking77.yaml
evals/registry/evals/beam-analysis.yaml
evals/registry/evals/belarusian-grammar.yaml
evals/registry/evals/belarusian-lexicon.yaml
evals/registry/evals/belarusian-numerals.yaml
evals/registry/evals/belarusian-proverbs.yaml
evals/registry/evals/belarusian-rhyme.yaml
evals/registry/evals/belarusian-russian-translation.yaml
evals/registry/evals/belarusian-syllable-count.yaml
evals/registry/evals/belarusian-synonyms.yaml
evals/registry/evals/bigrams.yaml
evals/registry/evals/bitwise.yaml
evals/registry/evals/body-movement.yaml
evals/registry/evals/born-first.yaml
evals/registry/evals/brazilian-lexicon.yaml
evals/registry/evals/brazilian_laws.yaml
evals/registry/evals/building_floorplan.yaml
evals/registry/evals/bulgarian-lexicon.yaml
evals/registry/evals/canto_wu_pronunciation.yaml
evals/registry/evals/canto_wu_pronunciation_fewshot.yaml
evals/registry/evals/cardinal-directions.yaml
evals/registry/evals/categorize_with_distractors.yaml
evals/registry/evals/chess-piece-count.yaml
evals/registry/evals/chess.yaml
evals/registry/evals/chinese_hard_translations.yaml
evals/registry/evals/chinese_homonym.yaml
evals/registry/evals/chinese_poem.yaml
evals/registry/evals/chinese_song_ci.yaml
evals/registry/evals/chinese_tang_poetries.yaml
evals/registry/evals/chinese_zodiac.yaml
evals/registry/evals/cissp-study-questions.yaml
evals/registry/evals/code_combination.yaml
evals/registry/evals/color_theory_complementary.yaml
evals/registry/evals/compare-countries-area.yaml
evals/registry/evals/complex-analogies-en-ru.yaml
evals/registry/evals/complex-replace-characters.yaml
evals/registry/evals/comprehensive-graph-reasoning.yaml
evals/registry/evals/connect-4.yaml
evals/registry/evals/consensus_summary.yaml
evals/registry/evals/context-free-grammar.yaml
evals/registry/evals/convert-hex-hsl-lightness.yaml
evals/registry/evals/coqa-ex.yaml
evals/registry/evals/count_intersections_polynomial.yaml
evals/registry/evals/count_token_freq_dna.yaml
evals/registry/evals/counterfactual-reasoning.yaml
evals/registry/evals/countries.yaml
evals/registry/evals/crepe.yaml
evals/registry/evals/cricket_situations.yaml
evals/registry/evals/crontab.yaml
evals/registry/evals/cube-pack.yaml
evals/registry/evals/cybersecurity-filepaths.yaml
evals/registry/evals/date-booking.yaml
evals/registry/evals/date-calculator.yaml
evals/registry/evals/day-of-week-from-date.yaml
evals/registry/evals/decrypt-caesar-cipher.yaml
evals/registry/evals/detect-hshd.yaml
evals/registry/evals/determinant.yaml
evals/registry/evals/diabetes.yaml
evals/registry/evals/diagrammatic_logic.yaml
evals/registry/evals/dice-rotation-sequence.yaml
evals/registry/evals/direct-speech-tag.yaml
evals/registry/evals/directions.yaml
evals/registry/evals/dna-melting-calculation.yaml
evals/registry/evals/dutch-lexicon.yaml
evals/registry/evals/emoji-riddle.yaml
evals/registry/evals/emotional-intelligence.yaml
evals/registry/evals/escher-sentences.yaml
evals/registry/evals/euler_problems.yaml
evals/registry/evals/european-date-format-challenge.yaml
evals/registry/evals/event-categories.yaml
evals/registry/evals/fcc_amateur_extra.yaml
evals/registry/evals/finance.yaml
evals/registry/evals/financial-derivatives.yaml
evals/registry/evals/find-letter.yaml
evals/registry/evals/find-thirukkural.yaml
evals/registry/evals/find_country_from_svg.yaml
evals/registry/evals/finnish-rhyme.yaml
evals/registry/evals/first-letters.yaml
evals/registry/evals/food.yaml
evals/registry/evals/formal-grammar-to-regex.yaml
evals/registry/evals/formal_logic.yaml
evals/registry/evals/forth-stack-sim.yaml
evals/registry/evals/french-lexicon.yaml
evals/registry/evals/french-part-of-speech.yaml
evals/registry/evals/game-theory.yaml
evals/registry/evals/geometry_puzzle.yaml
evals/registry/evals/german-part-of-speech.yaml
evals/registry/evals/gol.yaml
evals/registry/evals/gpt-protocol-buffers.yaml
evals/registry/evals/greek-nt-manuscripts.yaml
evals/registry/evals/greek-vocabulary.yaml
evals/registry/evals/guess-the-singer.yaml
evals/registry/evals/heart-disease.yaml
evals/registry/evals/hebrew-bible.yaml
evals/registry/evals/hebrew-rhyme.yaml
evals/registry/evals/hebrew-same-noun-gender.yaml
evals/registry/evals/hebrew_talmud_suka.yaml
evals/registry/evals/hindi_shuddha.yaml
evals/registry/evals/hindi_upsc.yaml
evals/registry/evals/hindi_words.yaml
evals/registry/evals/historical-kana-orthography-reading.yaml
evals/registry/evals/human-safety.yaml
evals/registry/evals/iambic-pentameter.yaml
evals/registry/evals/illinois-law.yaml
evals/registry/evals/imperial_date_to_string.yaml
evals/registry/evals/indonesian_numbers.yaml
evals/registry/evals/infiniteloop-match.yaml
evals/registry/evals/integer-sequence-predictions.yaml
evals/registry/evals/internal_representations.yaml
evals/registry/evals/invert_word_wise.yaml
evals/registry/evals/invoice_due_date_leap_day_adjustment.yaml
evals/registry/evals/invoices.yaml
evals/registry/evals/irish-lexicon.yaml
evals/registry/evals/irony.yaml
evals/registry/evals/islands.yaml
evals/registry/evals/isosceles-right-triangle.yaml
evals/registry/evals/italian-new-words.yaml
evals/registry/evals/italian-rhyme.yaml
evals/registry/evals/japanese-decimal-units.yaml
evals/registry/evals/japanese-itpassport-exam01.yaml
evals/registry/evals/japanese-national-medical-exam01.yaml
evals/registry/evals/japanese-national-medical-exam02.yaml
evals/registry/evals/japanese_city_name_pronuciation.yaml
evals/registry/evals/japanese_driving_license.yaml
evals/registry/evals/japanese_number_reading.yaml
evals/registry/evals/japanese_onomatopoeia.yaml
evals/registry/evals/japanese_populer_video_game_title_and_the_publisher.yaml
evals/registry/evals/jee-math.yaml
evals/registry/evals/job_listing_title_for_a_caregiver_in_japan.yaml
evals/registry/evals/json_patch_object.yaml
evals/registry/evals/kanji-idioms.yaml
evals/registry/evals/knot-theory.yaml
evals/registry/evals/korean-consonant-vowel-combination.yaml
evals/registry/evals/korean-phonetics.yaml
evals/registry/evals/korean_dialects.yaml
evals/registry/evals/korean_spelling.yaml
evals/registry/evals/korean_yaminjeongeum.yaml
evals/registry/evals/language.yaml
evals/registry/evals/largest_country.yaml
evals/registry/evals/last-word-nth.yaml
evals/registry/evals/lat_long_identify.yaml
evals/registry/evals/linear-equations.yaml
evals/registry/evals/linear-regression.yaml
evals/registry/evals/list_comparison_missing_name.yaml
evals/registry/evals/logic-grid-eval.yaml
evals/registry/evals/logic-liar-paradox.yaml
evals/registry/evals/logic-riddles.yaml
evals/registry/evals/logic-statements.yaml
evals/registry/evals/logic.yaml
evals/registry/evals/logic_and_probability.yaml
evals/registry/evals/logical_counting.yaml
evals/registry/evals/logical_reasoning_letter_series_test.yaml
evals/registry/evals/logiqa-logical-reasoning-plus.yaml
evals/registry/evals/logiqa.yaml
evals/registry/evals/loss-logic.yaml
evals/registry/evals/lunar-calendar.yaml
evals/registry/evals/mandaliof-table.yaml
evals/registry/evals/manga-translation.yaml
evals/registry/evals/map-electronic-component-part-to-fact.yaml
evals/registry/evals/mapping_to_matricies.yaml
evals/registry/evals/mate-in-one.yaml
evals/registry/evals/math_logic_operations.yaml
evals/registry/evals/math_polish.yaml
evals/registry/evals/matrix-mult-rows.yaml
evals/registry/evals/mazes.yaml
evals/registry/evals/medication_dose.yaml
evals/registry/evals/medmcqa.yaml
evals/registry/evals/mendelian_inheritance.yaml
evals/registry/evals/missing-operators.yaml
evals/registry/evals/mmlu.yaml
evals/registry/evals/monthly_metric_comparison.yaml
evals/registry/evals/moral_exceptQA.yaml
evals/registry/evals/multi-step-equations.yaml
evals/registry/evals/multistep-word-problems.yaml
evals/registry/evals/music-theory-chord-names.yaml
evals/registry/evals/music-theory-chord-notes.yaml
evals/registry/evals/music-theory.yaml
evals/registry/evals/music_theory_scale_modes.yaml
evals/registry/evals/naughty_strings.yaml
evals/registry/evals/nepali-song-singer.yaml
evals/registry/evals/newsology.yaml
evals/registry/evals/next-val-series.yaml
evals/registry/evals/nfl-point-combinations.yaml
evals/registry/evals/non-compound-names.yaml
evals/registry/evals/norwegian-lexicon.yaml
evals/registry/evals/number-pattern.yaml
evals/registry/evals/number-reading.yaml
evals/registry/evals/numbers_game.yaml
evals/registry/evals/numeral-type-comparisons.yaml
evals/registry/evals/nutrition.yaml
evals/registry/evals/ordered-history-events.yaml
evals/registry/evals/override-system-instruction.yaml
evals/registry/evals/pantone_to_hex.yaml
evals/registry/evals/parable-to-moral-match.yaml
evals/registry/evals/pararule-plus-multi-step-deductive-reasoning.yaml
evals/registry/evals/partially_solved_crossword_clues.yaml
evals/registry/evals/passing-balls.yaml
evals/registry/evals/path_enclosed_area.yaml
evals/registry/evals/pattern_identification.yaml
evals/registry/evals/ph_calculation.yaml
evals/registry/evals/phonetics-identify-words-needing-missing-gpcs.yaml
evals/registry/evals/physics-interaction.yaml
evals/registry/evals/pointer-value-retrieval.yaml
evals/registry/evals/points-on-line.yaml
evals/registry/evals/poker_analysis.yaml
evals/registry/evals/poker_hand_ranks.yaml
evals/registry/evals/polish-lexicon.yaml
evals/registry/evals/polish-syllable-count.yaml
evals/registry/evals/polish_rhymes_generation.yaml
evals/registry/evals/population_span_extraction.yaml
evals/registry/evals/portuguese-kinship-riddles.yaml
evals/registry/evals/portuguese-sarcasm.yaml
evals/registry/evals/portuguese-syllable-count.yaml
evals/registry/evals/positive-binary-operations.yaml
evals/registry/evals/probability_questions.yaml
evals/registry/evals/product-matching.yaml
evals/registry/evals/prompt-injection.yaml
evals/registry/evals/pure_korean.yaml
evals/registry/evals/python_list_comprehension.yaml
evals/registry/evals/qa.yaml
evals/registry/evals/quartz.yaml
evals/registry/evals/rare-and-loanwords-dutch-lexicon.yaml
evals/registry/evals/raven-matrices.yaml
evals/registry/evals/rectangles.yaml
evals/registry/evals/regex-match.yaml
evals/registry/evals/resistor-ohm-calculator.yaml
evals/registry/evals/resource_id_extraction.yaml
evals/registry/evals/reverse-polish-notation.yaml
evals/registry/evals/reverse-sort-words-eng.yaml
evals/registry/evals/reverse-string.yaml
evals/registry/evals/rhetorical-devices.yaml
evals/registry/evals/rock-climbing.yaml
evals/registry/evals/rot13.yaml
evals/registry/evals/ru_rhymes.yaml
evals/registry/evals/rubiks-colors.yaml
evals/registry/evals/rucola.yaml
evals/registry/evals/russe.yaml
evals/registry/evals/russian-english-homonym-context-resolution.yaml
evals/registry/evals/russian-lexicon.yaml
evals/registry/evals/russian-nlp-tasks.yaml
evals/registry/evals/russian-rhyme.yaml
evals/registry/evals/russian-verse.yaml
evals/registry/evals/russian_medical.yaml
evals/registry/evals/russian_sarcasm.yaml
evals/registry/evals/sarcasm.yaml
evals/registry/evals/seating_arrangements.yaml
evals/registry/evals/security_guide.yaml
evals/registry/evals/sexagenary-cycle-calculation.yaml
evals/registry/evals/shape-in-shape.yaml
evals/registry/evals/shared-borders.yaml
evals/registry/evals/shopping_discount_comparison.yaml
evals/registry/evals/simple-knowledge-mongolian.yaml
evals/registry/evals/simple-visual-understanding.yaml
evals/registry/evals/simple_math.yaml
evals/registry/evals/simple_physics_engine.yaml
evals/registry/evals/sindarin-fluency.yaml
evals/registry/evals/soc_codes.yaml
evals/registry/evals/solve-for-variable.yaml
evals/registry/evals/sort-numeric.yaml
evals/registry/evals/south-african-bands.yaml
evals/registry/evals/spanish-lexicon.yaml
evals/registry/evals/spanish_feminine_noun_masculine_article.yaml
evals/registry/evals/split_chinese_characters.yaml
evals/registry/evals/sql.yaml
evals/registry/evals/squares-gpt.yaml
evals/registry/evals/stats-tests.yaml
evals/registry/evals/stock-options.yaml
evals/registry/evals/superficial-patterns.yaml
evals/registry/evals/svg_to_text.yaml
evals/registry/evals/svg_understanding.yaml
evals/registry/evals/swap-words.yaml
evals/registry/evals/swedish-spelling.yaml
evals/registry/evals/swedish_sat.yaml
evals/registry/evals/syllables_long_words.yaml
evals/registry/evals/syntax-check.yaml
evals/registry/evals/taxes.yaml
evals/registry/evals/tempo_to_measure_count.yaml
evals/registry/evals/test-basic.yaml
evals/registry/evals/test-comp-sci.yaml
evals/registry/evals/test-modelgraded-battle.yaml
evals/registry/evals/test-modelgraded-generated.yaml
evals/registry/evals/test-modelgraded.yaml
evals/registry/evals/test_japanese_radical.yaml
evals/registry/evals/test_japanese_units.yaml
evals/registry/evals/tetris.yaml
evals/registry/evals/three-pt-mapping.yaml
evals/registry/evals/time-zone-conversion.yaml
evals/registry/evals/track_objects.yaml
evals/registry/evals/tracking-shuffled-objects.yaml
evals/registry/evals/turkish_characters.yaml
evals/registry/evals/ukraine-eit.yaml
evals/registry/evals/ukraine-gec.yaml
evals/registry/evals/ukraine_electronic_petitions.yaml
evals/registry/evals/unified-patch.yaml
evals/registry/evals/unique_combinations.yaml
evals/registry/evals/unsolvable_questions.yaml
evals/registry/evals/unwanted-rhyming.yaml
evals/registry/evals/us-tort-law.yaml
evals/registry/evals/utah_real_estate.yaml
evals/registry/evals/utility_price_parsing.yaml
evals/registry/evals/vigenere.yaml
evals/registry/evals/vintage_phone_keyboard_decode.yaml
evals/registry/evals/which-is-heavier.yaml
evals/registry/evals/wkt_understanding.yaml
evals/registry/evals/word_vector_over_reliance.yaml
evals/registry/modelgraded/battle.yaml
evals/registry/modelgraded/best.yaml
evals/registry/modelgraded/closedqa.yaml
evals/registry/modelgraded/diversity.yaml
evals/registry/modelgraded/fact.yaml
evals/registry/modelgraded/humor.yaml
evals/registry/modelgraded/iambic_pentameter.yaml
evals/registry/modelgraded/onomatopoeia.yaml
evals/registry/modelgraded/regression-equation.yaml
evals/registry/modelgraded/rhyming.yaml
evals/registry/modelgraded/security.yaml
evals/registry/modelgraded/sql.yaml
evals/utils/api_utils.py
evals/utils/misc.py
evals/utils/snowflake.py
evals/utils/test.py
evals_nightly.egg-info/PKG-INFO
evals_nightly.egg-info/SOURCES.txt
evals_nightly.egg-info/dependency_links.txt
evals_nightly.egg-info/entry_points.txt
evals_nightly.egg-info/requires.txt
evals_nightly.egg-info/top_level.txt