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/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/translate.py
evals/elsuite/utils.py
evals/elsuite/basic/fuzzy_match.py
evals/elsuite/basic/fuzzy_match_test.py
evals/elsuite/basic/includes.py
evals/elsuite/basic/json_validator.py
evals/elsuite/basic/match.py
evals/elsuite/modelgraded/base.py
evals/elsuite/modelgraded/classify.py
evals/elsuite/modelgraded/classify_utils.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/manga-translation.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/evals/aba-mrpc-true-false.yaml
evals/registry/evals/actors-sequence.yaml
evals/registry/evals/algebra-word-problems.yaml
evals/registry/evals/anagrams.yaml
evals/registry/evals/balance-chemical-equation.yaml
evals/registry/evals/banking77.yaml
evals/registry/evals/belarusian-lexicon.yaml
evals/registry/evals/bigrams.yaml
evals/registry/evals/bitwise.yaml
evals/registry/evals/born-first.yaml
evals/registry/evals/brazilian-lexicon.yaml
evals/registry/evals/bulgarian-lexicon.yaml
evals/registry/evals/categorize_with_distractors.yaml
evals/registry/evals/chess-piece-count.yaml
evals/registry/evals/chess.yaml
evals/registry/evals/compare-countries-area.yaml
evals/registry/evals/complex-replace-characters.yaml
evals/registry/evals/connect-4.yaml
evals/registry/evals/convert-hex-hsl-lightness.yaml
evals/registry/evals/coqa-ex.yaml
evals/registry/evals/crepe.yaml
evals/registry/evals/cube-pack.yaml
evals/registry/evals/decrypt-caesar-cipher.yaml
evals/registry/evals/determinant.yaml
evals/registry/evals/diagrammatic_logic.yaml
evals/registry/evals/dice-rotation-sequence.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/fcc_amateur_extra.yaml
evals/registry/evals/finance.yaml
evals/registry/evals/first-letters.yaml
evals/registry/evals/formal_logic.yaml
evals/registry/evals/forth-stack-sim.yaml
evals/registry/evals/greek-vocabulary.yaml
evals/registry/evals/heart-disease.yaml
evals/registry/evals/hebrew-rhyme.yaml
evals/registry/evals/hindi_upsc.yaml
evals/registry/evals/illinois-law.yaml
evals/registry/evals/imperial_date_to_string.yaml
evals/registry/evals/infiniteloop-match.yaml
evals/registry/evals/invoices.yaml
evals/registry/evals/japanese-national-medical-exam01.yaml
evals/registry/evals/japanese_driving_license.yaml
evals/registry/evals/job_listing_title_for_a_caregiver_in_japan.yaml
evals/registry/evals/knot-theory.yaml
evals/registry/evals/last-word-nth.yaml
evals/registry/evals/lat_long_identify.yaml
evals/registry/evals/logic-statements.yaml
evals/registry/evals/logic.yaml
evals/registry/evals/logiqa.yaml
evals/registry/evals/loss-logic.yaml
evals/registry/evals/manga-translation.yaml
evals/registry/evals/map-electronic-component-part-to-fact.yaml
evals/registry/evals/medmcqa.yaml
evals/registry/evals/mendelian_inheritance.yaml
evals/registry/evals/moral_exceptQA.yaml
evals/registry/evals/multi-step-equations.yaml
evals/registry/evals/naughty_strings.yaml
evals/registry/evals/number-pattern.yaml
evals/registry/evals/number-reading.yaml
evals/registry/evals/partially_solved_crossword_clues.yaml
evals/registry/evals/pattern_identification.yaml
evals/registry/evals/ph_calculation.yaml
evals/registry/evals/poker_hand_ranks.yaml
evals/registry/evals/positive-binary-operations.yaml
evals/registry/evals/qa.yaml
evals/registry/evals/regex-match.yaml
evals/registry/evals/reverse-string.yaml
evals/registry/evals/rot13.yaml
evals/registry/evals/rucola.yaml
evals/registry/evals/russe.yaml
evals/registry/evals/russian-nlp-tasks.yaml
evals/registry/evals/russian-rhyme.yaml
evals/registry/evals/russian_medical.yaml
evals/registry/evals/sarcasm.yaml
evals/registry/evals/simple-knowledge-mongolian.yaml
evals/registry/evals/sort-numeric.yaml
evals/registry/evals/sql.yaml
evals/registry/evals/stock-options.yaml
evals/registry/evals/svg_understanding.yaml
evals/registry/evals/swedish-spelling.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/three-pt-mapping.yaml
evals/registry/evals/ukraine-eit.yaml
evals/registry/evals/unified-patch.yaml
evals/registry/evals/us-tort-law.yaml
evals/registry/evals/utility_price_parsing.yaml
evals/registry/evals/which-is-heavier.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/security.yaml
evals/registry/modelgraded/sql.yaml
evals/utils/api_utils.py
evals/utils/misc.py
evals/utils/snowflake.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