task_table.md

Task Name	Train	Val	Test	Val/Test Docs	Metrics
anagrams1		✓		10000	acc
anagrams2		✓		10000	acc
anli_r1	✓	✓	✓	1000	acc
anli_r2	✓	✓	✓	1000	acc
anli_r3	✓	✓	✓	1200	acc
arc_challenge	✓	✓	✓	1172	acc, acc_norm
arc_easy	✓	✓	✓	2376	acc, acc_norm
arithmetic_1dc		✓		2000	acc
arithmetic_2da		✓		2000	acc
arithmetic_2dm		✓		2000	acc
arithmetic_2ds		✓		2000	acc
arithmetic_3da		✓		2000	acc
arithmetic_3ds		✓		2000	acc
arithmetic_4da		✓		2000	acc
arithmetic_4ds		✓		2000	acc
arithmetic_5da		✓		2000	acc
arithmetic_5ds		✓		2000	acc
bigbench_causal_judgement			✓	190	multiple_choice_grade, exact_str_match
bigbench_date_understanding			✓	369	multiple_choice_grade, exact_str_match
bigbench_disambiguation_qa			✓	258	multiple_choice_grade, exact_str_match
bigbench_dyck_languages			✓	1000	multiple_choice_grade, exact_str_match
bigbench_formal_fallacies_syllogisms_negation			✓	14200	multiple_choice_grade, exact_str_match
bigbench_geometric_shapes			✓	359	multiple_choice_grade, exact_str_match
bigbench_hyperbaton			✓	50000	multiple_choice_grade, exact_str_match
bigbench_logical_deduction_five_objects			✓	500	multiple_choice_grade, exact_str_match
bigbench_logical_deduction_seven_objects			✓	700	multiple_choice_grade, exact_str_match
bigbench_logical_deduction_three_objects			✓	300	multiple_choice_grade, exact_str_match
bigbench_movie_recommendation			✓	500	multiple_choice_grade, exact_str_match
bigbench_navigate			✓	1000	multiple_choice_grade, exact_str_match
bigbench_reasoning_about_colored_objects			✓	2000	multiple_choice_grade, exact_str_match
bigbench_ruin_names			✓	448	multiple_choice_grade, exact_str_match
bigbench_salient_translation_error_detection			✓	998	multiple_choice_grade, exact_str_match
bigbench_snarks			✓	181	multiple_choice_grade, exact_str_match
bigbench_sports_understanding			✓	986	multiple_choice_grade, exact_str_match
bigbench_temporal_sequences			✓	1000	multiple_choice_grade, exact_str_match
bigbench_tracking_shuffled_objects_five_objects			✓	1250	multiple_choice_grade, exact_str_match
bigbench_tracking_shuffled_objects_seven_objects			✓	1750	multiple_choice_grade, exact_str_match
bigbench_tracking_shuffled_objects_three_objects			✓	300	multiple_choice_grade, exact_str_match
blimp_adjunct_island		✓		1000	acc
blimp_anaphor_gender_agreement		✓		1000	acc
blimp_anaphor_number_agreement		✓		1000	acc
blimp_animate_subject_passive		✓		1000	acc
blimp_animate_subject_trans		✓		1000	acc
blimp_causative		✓		1000	acc
blimp_complex_NP_island		✓		1000	acc
blimp_coordinate_structure_constraint_complex_left_branch		✓		1000	acc
blimp_coordinate_structure_constraint_object_extraction		✓		1000	acc
blimp_determiner_noun_agreement_1		✓		1000	acc
blimp_determiner_noun_agreement_2		✓		1000	acc
blimp_determiner_noun_agreement_irregular_1		✓		1000	acc
blimp_determiner_noun_agreement_irregular_2		✓		1000	acc
blimp_determiner_noun_agreement_with_adj_2		✓		1000	acc
blimp_determiner_noun_agreement_with_adj_irregular_1		✓		1000	acc
blimp_determiner_noun_agreement_with_adj_irregular_2		✓		1000	acc
blimp_determiner_noun_agreement_with_adjective_1		✓		1000	acc
blimp_distractor_agreement_relational_noun		✓		1000	acc
blimp_distractor_agreement_relative_clause		✓		1000	acc
blimp_drop_argument		✓		1000	acc
blimp_ellipsis_n_bar_1		✓		1000	acc
blimp_ellipsis_n_bar_2		✓		1000	acc
blimp_existential_there_object_raising		✓		1000	acc
blimp_existential_there_quantifiers_1		✓		1000	acc
blimp_existential_there_quantifiers_2		✓		1000	acc
blimp_existential_there_subject_raising		✓		1000	acc
blimp_expletive_it_object_raising		✓		1000	acc
blimp_inchoative		✓		1000	acc
blimp_intransitive		✓		1000	acc
blimp_irregular_past_participle_adjectives		✓		1000	acc
blimp_irregular_past_participle_verbs		✓		1000	acc
blimp_irregular_plural_subject_verb_agreement_1		✓		1000	acc
blimp_irregular_plural_subject_verb_agreement_2		✓		1000	acc
blimp_left_branch_island_echo_question		✓		1000	acc
blimp_left_branch_island_simple_question		✓		1000	acc
blimp_matrix_question_npi_licensor_present		✓		1000	acc
blimp_npi_present_1		✓		1000	acc
blimp_npi_present_2		✓		1000	acc
blimp_only_npi_licensor_present		✓		1000	acc
blimp_only_npi_scope		✓		1000	acc
blimp_passive_1		✓		1000	acc
blimp_passive_2		✓		1000	acc
blimp_principle_A_c_command		✓		1000	acc
blimp_principle_A_case_1		✓		1000	acc
blimp_principle_A_case_2		✓		1000	acc
blimp_principle_A_domain_1		✓		1000	acc
blimp_principle_A_domain_2		✓		1000	acc
blimp_principle_A_domain_3		✓		1000	acc
blimp_principle_A_reconstruction		✓		1000	acc
blimp_regular_plural_subject_verb_agreement_1		✓		1000	acc
blimp_regular_plural_subject_verb_agreement_2		✓		1000	acc
blimp_sentential_negation_npi_licensor_present		✓		1000	acc
blimp_sentential_negation_npi_scope		✓		1000	acc
blimp_sentential_subject_island		✓		1000	acc
blimp_superlative_quantifiers_1		✓		1000	acc
blimp_superlative_quantifiers_2		✓		1000	acc
blimp_tough_vs_raising_1		✓		1000	acc
blimp_tough_vs_raising_2		✓		1000	acc
blimp_transitive		✓		1000	acc
blimp_wh_island		✓		1000	acc
blimp_wh_questions_object_gap		✓		1000	acc
blimp_wh_questions_subject_gap		✓		1000	acc
blimp_wh_questions_subject_gap_long_distance		✓		1000	acc
blimp_wh_vs_that_no_gap		✓		1000	acc
blimp_wh_vs_that_no_gap_long_distance		✓		1000	acc
blimp_wh_vs_that_with_gap		✓		1000	acc
blimp_wh_vs_that_with_gap_long_distance		✓		1000	acc
boolq	✓	✓		3270	acc
cb	✓	✓		56	acc, f1
cola	✓	✓		1043	mcc
copa	✓	✓		100	acc
coqa	✓	✓		500	f1, em
crows_pairs_english		✓		1677	likelihood_difference, pct_stereotype
crows_pairs_english_age		✓		91	likelihood_difference, pct_stereotype
crows_pairs_english_autre		✓		11	likelihood_difference, pct_stereotype
crows_pairs_english_disability		✓		65	likelihood_difference, pct_stereotype
crows_pairs_english_gender		✓		320	likelihood_difference, pct_stereotype
crows_pairs_english_nationality		✓		216	likelihood_difference, pct_stereotype
crows_pairs_english_physical_appearance		✓		72	likelihood_difference, pct_stereotype
crows_pairs_english_race_color		✓		508	likelihood_difference, pct_stereotype
crows_pairs_english_religion		✓		111	likelihood_difference, pct_stereotype
crows_pairs_english_sexual_orientation		✓		93	likelihood_difference, pct_stereotype
crows_pairs_english_socioeconomic		✓		190	likelihood_difference, pct_stereotype
crows_pairs_french		✓		1677	likelihood_difference, pct_stereotype
crows_pairs_french_age		✓		90	likelihood_difference, pct_stereotype
crows_pairs_french_autre		✓		13	likelihood_difference, pct_stereotype
crows_pairs_french_disability		✓		66	likelihood_difference, pct_stereotype
crows_pairs_french_gender		✓		321	likelihood_difference, pct_stereotype
crows_pairs_french_nationality		✓		253	likelihood_difference, pct_stereotype
crows_pairs_french_physical_appearance		✓		72	likelihood_difference, pct_stereotype
crows_pairs_french_race_color		✓		460	likelihood_difference, pct_stereotype
crows_pairs_french_religion		✓		115	likelihood_difference, pct_stereotype
crows_pairs_french_sexual_orientation		✓		91	likelihood_difference, pct_stereotype
crows_pairs_french_socioeconomic		✓		196	likelihood_difference, pct_stereotype
cycle_letters		✓		10000	acc
drop	✓	✓		9536	em, f1
ethics_cm	✓		✓	3885	acc
ethics_deontology	✓		✓	3596	acc, em
ethics_justice	✓		✓	2704	acc, em
ethics_utilitarianism	✓		✓	4808	acc
ethics_utilitarianism_original			✓	4808	acc
ethics_virtue	✓		✓	4975	acc, em
gsm8k	✓		✓	1319	acc
headqa	✓	✓	✓	2742	acc, acc_norm
headqa_en	✓	✓	✓	2742	acc, acc_norm
headqa_es	✓	✓	✓	2742	acc, acc_norm
hellaswag	✓	✓		10042	acc, acc_norm
hendrycksTest-abstract_algebra		✓	✓	100	acc, acc_norm
hendrycksTest-anatomy		✓	✓	135	acc, acc_norm
hendrycksTest-astronomy		✓	✓	152	acc, acc_norm
hendrycksTest-business_ethics		✓	✓	100	acc, acc_norm
hendrycksTest-clinical_knowledge		✓	✓	265	acc, acc_norm
hendrycksTest-college_biology		✓	✓	144	acc, acc_norm
hendrycksTest-college_chemistry		✓	✓	100	acc, acc_norm
hendrycksTest-college_computer_science		✓	✓	100	acc, acc_norm
hendrycksTest-college_mathematics		✓	✓	100	acc, acc_norm
hendrycksTest-college_medicine		✓	✓	173	acc, acc_norm
hendrycksTest-college_physics		✓	✓	102	acc, acc_norm
hendrycksTest-computer_security		✓	✓	100	acc, acc_norm
hendrycksTest-conceptual_physics		✓	✓	235	acc, acc_norm
hendrycksTest-econometrics		✓	✓	114	acc, acc_norm
hendrycksTest-electrical_engineering		✓	✓	145	acc, acc_norm
hendrycksTest-elementary_mathematics		✓	✓	378	acc, acc_norm
hendrycksTest-formal_logic		✓	✓	126	acc, acc_norm
hendrycksTest-global_facts		✓	✓	100	acc, acc_norm
hendrycksTest-high_school_biology		✓	✓	310	acc, acc_norm
hendrycksTest-high_school_chemistry		✓	✓	203	acc, acc_norm
hendrycksTest-high_school_computer_science		✓	✓	100	acc, acc_norm
hendrycksTest-high_school_european_history		✓	✓	165	acc, acc_norm
hendrycksTest-high_school_geography		✓	✓	198	acc, acc_norm
hendrycksTest-high_school_government_and_politics		✓	✓	193	acc, acc_norm
hendrycksTest-high_school_macroeconomics		✓	✓	390	acc, acc_norm
hendrycksTest-high_school_mathematics		✓	✓	270	acc, acc_norm
hendrycksTest-high_school_microeconomics		✓	✓	238	acc, acc_norm
hendrycksTest-high_school_physics		✓	✓	151	acc, acc_norm
hendrycksTest-high_school_psychology		✓	✓	545	acc, acc_norm
hendrycksTest-high_school_statistics		✓	✓	216	acc, acc_norm
hendrycksTest-high_school_us_history		✓	✓	204	acc, acc_norm
hendrycksTest-high_school_world_history		✓	✓	237	acc, acc_norm
hendrycksTest-human_aging		✓	✓	223	acc, acc_norm
hendrycksTest-human_sexuality		✓	✓	131	acc, acc_norm
hendrycksTest-international_law		✓	✓	121	acc, acc_norm
hendrycksTest-jurisprudence		✓	✓	108	acc, acc_norm
hendrycksTest-logical_fallacies		✓	✓	163	acc, acc_norm
hendrycksTest-machine_learning		✓	✓	112	acc, acc_norm
hendrycksTest-management		✓	✓	103	acc, acc_norm
hendrycksTest-marketing		✓	✓	234	acc, acc_norm
hendrycksTest-medical_genetics		✓	✓	100	acc, acc_norm
hendrycksTest-miscellaneous		✓	✓	783	acc, acc_norm
hendrycksTest-moral_disputes		✓	✓	346	acc, acc_norm
hendrycksTest-moral_scenarios		✓	✓	895	acc, acc_norm
hendrycksTest-nutrition		✓	✓	306	acc, acc_norm
hendrycksTest-philosophy		✓	✓	311	acc, acc_norm
hendrycksTest-prehistory		✓	✓	324	acc, acc_norm
hendrycksTest-professional_accounting		✓	✓	282	acc, acc_norm
hendrycksTest-professional_law		✓	✓	1534	acc, acc_norm
hendrycksTest-professional_medicine		✓	✓	272	acc, acc_norm
hendrycksTest-professional_psychology		✓	✓	612	acc, acc_norm
hendrycksTest-public_relations		✓	✓	110	acc, acc_norm
hendrycksTest-security_studies		✓	✓	245	acc, acc_norm
hendrycksTest-sociology		✓	✓	201	acc, acc_norm
hendrycksTest-us_foreign_policy		✓	✓	100	acc, acc_norm
hendrycksTest-virology		✓	✓	166	acc, acc_norm
hendrycksTest-world_religions		✓	✓	171	acc, acc_norm
iwslt17-ar-en			✓	1460	bleu, chrf, ter
iwslt17-en-ar			✓	1460	bleu, chrf, ter
lambada_openai			✓	5153	ppl, acc
lambada_openai_cloze			✓	5153	ppl, acc
lambada_openai_mt_de			✓	5153	ppl, acc
lambada_openai_mt_en			✓	5153	ppl, acc
lambada_openai_mt_es			✓	5153	ppl, acc
lambada_openai_mt_fr			✓	5153	ppl, acc
lambada_openai_mt_it			✓	5153	ppl, acc
lambada_standard		✓	✓	5153	ppl, acc
lambada_standard_cloze		✓	✓	5153	ppl, acc
logiqa	✓	✓	✓	651	acc, acc_norm
math_algebra	✓		✓	1187	acc
math_asdiv		✓		2305	acc
math_counting_and_prob	✓		✓	474	acc
math_geometry	✓		✓	479	acc
math_intermediate_algebra	✓		✓	903	acc
math_num_theory	✓		✓	540	acc
math_prealgebra	✓		✓	871	acc
math_precalc	✓		✓	546	acc
mathqa	✓	✓	✓	2985	acc, acc_norm
mc_taco		✓	✓	9442	f1, em
mgsm_bn	✓		✓	250	acc
mgsm_de	✓		✓	250	acc
mgsm_en	✓		✓	250	acc
mgsm_es	✓		✓	250	acc
mgsm_fr	✓		✓	250	acc
mgsm_ja	✓		✓	250	acc
mgsm_ru	✓		✓	250	acc
mgsm_sw	✓		✓	250	acc
mgsm_te	✓		✓	250	acc
mgsm_th	✓		✓	250	acc
mgsm_zh	✓		✓	250	acc
mnli	✓	✓		9815	acc
mnli_mismatched	✓	✓		9832	acc
mrpc	✓	✓		408	acc, f1
multirc	✓	✓		4848	acc
mutual	✓	✓		886	r@1, r@2, mrr
mutual_plus	✓	✓		886	r@1, r@2, mrr
nq_open		✓		3610	em
openbookqa	✓	✓	✓	500	acc, acc_norm
pawsx_de	✓	✓	✓	2000	acc
pawsx_en	✓	✓	✓	2000	acc
pawsx_es	✓	✓	✓	2000	acc
pawsx_fr	✓	✓	✓	2000	acc
pawsx_ja	✓	✓	✓	2000	acc
pawsx_ko	✓	✓	✓	2000	acc
pawsx_zh	✓	✓	✓	2000	acc
pile_arxiv		✓	✓	2407	word_perplexity, byte_perplexity, bits_per_byte
pile_bookcorpus2		✓	✓	28	word_perplexity, byte_perplexity, bits_per_byte
pile_books3		✓	✓	269	word_perplexity, byte_perplexity, bits_per_byte
pile_dm-mathematics		✓	✓	1922	word_perplexity, byte_perplexity, bits_per_byte
pile_enron		✓	✓	1010	word_perplexity, byte_perplexity, bits_per_byte
pile_europarl		✓	✓	157	word_perplexity, byte_perplexity, bits_per_byte
pile_freelaw		✓	✓	5101	word_perplexity, byte_perplexity, bits_per_byte
pile_github		✓	✓	18195	word_perplexity, byte_perplexity, bits_per_byte
pile_gutenberg		✓	✓	80	word_perplexity, byte_perplexity, bits_per_byte
pile_hackernews		✓	✓	1632	word_perplexity, byte_perplexity, bits_per_byte
pile_nih-exporter		✓	✓	1884	word_perplexity, byte_perplexity, bits_per_byte
pile_opensubtitles		✓	✓	642	word_perplexity, byte_perplexity, bits_per_byte
pile_openwebtext2		✓	✓	32925	word_perplexity, byte_perplexity, bits_per_byte
pile_philpapers		✓	✓	68	word_perplexity, byte_perplexity, bits_per_byte
pile_pile-cc		✓	✓	52790	word_perplexity, byte_perplexity, bits_per_byte
pile_pubmed-abstracts		✓	✓	29895	word_perplexity, byte_perplexity, bits_per_byte
pile_pubmed-central		✓	✓	5911	word_perplexity, byte_perplexity, bits_per_byte
pile_stackexchange		✓	✓	30378	word_perplexity, byte_perplexity, bits_per_byte
pile_ubuntu-irc		✓	✓	22	word_perplexity, byte_perplexity, bits_per_byte
pile_uspto		✓	✓	11415	word_perplexity, byte_perplexity, bits_per_byte
pile_wikipedia		✓	✓	17511	word_perplexity, byte_perplexity, bits_per_byte
pile_youtubesubtitles		✓	✓	342	word_perplexity, byte_perplexity, bits_per_byte
piqa	✓	✓		1838	acc, acc_norm
prost			✓	18736	acc, acc_norm
pubmedqa			✓	1000	acc
qa4mre_2011			✓	120	acc, acc_norm
qa4mre_2012			✓	160	acc, acc_norm
qa4mre_2013			✓	284	acc, acc_norm
qasper	✓	✓		1764	f1_yesno, f1_abstractive
qnli	✓	✓		5463	acc
qqp	✓	✓		40430	acc, f1
race	✓	✓	✓	1045	acc
random_insertion		✓		10000	acc
record	✓	✓		10000	f1, em
reversed_words		✓		10000	acc
rte	✓	✓		277	acc
sciq	✓	✓	✓	1000	acc, acc_norm
scrolls_contractnli	✓	✓		1037	em, acc, acc_norm
scrolls_govreport	✓	✓		972	rouge1, rouge2, rougeL
scrolls_narrativeqa	✓	✓		3425	f1
scrolls_qasper	✓	✓		984	f1
scrolls_qmsum	✓	✓		272	rouge1, rouge2, rougeL
scrolls_quality	✓	✓		2086	em, acc, acc_norm
scrolls_summscreenfd	✓	✓		338	rouge1, rouge2, rougeL
squad2	✓	✓		11873	exact, f1, HasAns_exact, HasAns_f1, NoAns_exact, NoAns_f1, best_exact, best_f1
sst	✓	✓		872	acc
swag	✓	✓		20006	acc, acc_norm
toxigen	✓		✓	940	acc, acc_norm
triviaqa	✓	✓		11313	acc
truthfulqa_gen		✓		817	bleurt_max, bleurt_acc, bleurt_diff, bleu_max, bleu_acc, bleu_diff, rouge1_max, rouge1_acc, rouge1_diff, rouge2_max, rouge2_acc, rouge2_diff, rougeL_max, rougeL_acc, rougeL_diff
truthfulqa_mc		✓		817	mc1, mc2
webqs	✓		✓	2032	acc
wic	✓	✓		638	acc
wikitext	✓	✓	✓	62	word_perplexity, byte_perplexity, bits_per_byte
winogrande	✓	✓		1267	acc
wmt14-en-fr			✓	3003	bleu, chrf, ter
wmt14-fr-en			✓	3003	bleu, chrf, ter
wmt16-de-en			✓	2999	bleu, chrf, ter
wmt16-en-de			✓	2999	bleu, chrf, ter
wmt16-en-ro			✓	1999	bleu, chrf, ter
wmt16-ro-en			✓	1999	bleu, chrf, ter
wmt20-cs-en			✓	664	bleu, chrf, ter
wmt20-de-en			✓	785	bleu, chrf, ter
wmt20-de-fr			✓	1619	bleu, chrf, ter
wmt20-en-cs			✓	1418	bleu, chrf, ter
wmt20-en-de			✓	1418	bleu, chrf, ter
wmt20-en-iu			✓	2971	bleu, chrf, ter
wmt20-en-ja			✓	1000	bleu, chrf, ter
wmt20-en-km			✓	2320	bleu, chrf, ter
wmt20-en-pl			✓	1000	bleu, chrf, ter
wmt20-en-ps			✓	2719	bleu, chrf, ter
wmt20-en-ru			✓	2002	bleu, chrf, ter
wmt20-en-ta			✓	1000	bleu, chrf, ter
wmt20-en-zh			✓	1418	bleu, chrf, ter
wmt20-fr-de			✓	1619	bleu, chrf, ter
wmt20-iu-en			✓	2971	bleu, chrf, ter
wmt20-ja-en			✓	993	bleu, chrf, ter
wmt20-km-en			✓	2320	bleu, chrf, ter
wmt20-pl-en			✓	1001	bleu, chrf, ter
wmt20-ps-en			✓	2719	bleu, chrf, ter
wmt20-ru-en			✓	991	bleu, chrf, ter
wmt20-ta-en			✓	997	bleu, chrf, ter
wmt20-zh-en			✓	2000	bleu, chrf, ter
wnli	✓	✓		71	acc
wsc	✓	✓		104	acc
wsc273			✓	273	acc
xcopa_et		✓	✓	500	acc
xcopa_ht		✓	✓	500	acc
xcopa_id		✓	✓	500	acc
xcopa_it		✓	✓	500	acc
xcopa_qu		✓	✓	500	acc
xcopa_sw		✓	✓	500	acc
xcopa_ta		✓	✓	500	acc
xcopa_th		✓	✓	500	acc
xcopa_tr		✓	✓	500	acc
xcopa_vi		✓	✓	500	acc
xcopa_zh		✓	✓	500	acc
xnli_ar	✓	✓	✓	5010	acc
xnli_bg	✓	✓	✓	5010	acc
xnli_de	✓	✓	✓	5010	acc
xnli_el	✓	✓	✓	5010	acc
xnli_en	✓	✓	✓	5010	acc
xnli_es	✓	✓	✓	5010	acc
xnli_fr	✓	✓	✓	5010	acc
xnli_hi	✓	✓	✓	5010	acc
xnli_ru	✓	✓	✓	5010	acc
xnli_sw	✓	✓	✓	5010	acc
xnli_th	✓	✓	✓	5010	acc
xnli_tr	✓	✓	✓	5010	acc
xnli_ur	✓	✓	✓	5010	acc
xnli_vi	✓	✓	✓	5010	acc
xnli_zh	✓	✓	✓	5010	acc
xstory_cloze_ar	✓	✓		1511	acc
xstory_cloze_en	✓	✓		1511	acc
xstory_cloze_es	✓	✓		1511	acc
xstory_cloze_eu	✓	✓		1511	acc
xstory_cloze_hi	✓	✓		1511	acc
xstory_cloze_id	✓	✓		1511	acc
xstory_cloze_my	✓	✓		1511	acc
xstory_cloze_ru	✓	✓		1511	acc
xstory_cloze_sw	✓	✓		1511	acc
xstory_cloze_te	✓	✓		1511	acc
xstory_cloze_zh	✓	✓		1511	acc
xwinograd_en			✓	2325	acc
xwinograd_fr			✓	83	acc
xwinograd_jp			✓	959	acc
xwinograd_pt			✓	263	acc
xwinograd_ru			✓	315	acc
xwinograd_zh			✓	504	acc
Ceval-valid-computer_network		✓		19	acc
Ceval-valid-operating_system		✓		19	acc
Ceval-valid-computer_architecture		✓		21	acc
Ceval-valid-college_programming		✓		37	acc
Ceval-valid-college_physics		✓		19	acc
Ceval-valid-college_chemistry		✓		24	acc
Ceval-valid-advanced_mathematics		✓		19	acc
Ceval-valid-probability_and_statistics		✓		18	acc
Ceval-valid-discrete_mathematics		✓		16	acc
Ceval-valid-electrical_engineer		✓		37	acc
Ceval-valid-metrology_engineer		✓		24	acc
Ceval-valid-high_school_mathematics		✓		18	acc
Ceval-valid-high_school_physics		✓		19	acc
Ceval-valid-high_school_chemistry		✓		19	acc
Ceval-valid-high_school_biology		✓		19	acc
Ceval-valid-middle_school_mathematics		✓		19	acc
Ceval-valid-middle_school_biology		✓		21	acc
Ceval-valid-middle_school_physics		✓		19	acc
Ceval-valid-middle_school_chemistry		✓		20	acc
Ceval-valid-veterinary_medicine		✓		23	acc
Ceval-valid-college_economics		✓		55	acc
Ceval-valid-business_administration		✓		33	acc
Ceval-valid-marxism		✓		19	acc
Ceval-valid-mao_zedong_thought		✓		24	acc
Ceval-valid-education_science		✓		29	acc
Ceval-valid-teacher_qualification		✓		44	acc
Ceval-valid-high_school_politics		✓		19	acc
Ceval-valid-high_school_geography		✓		19	acc
Ceval-valid-middle_school_politics		✓		21	acc
Ceval-valid-middle_school_geography		✓		12	acc
Ceval-valid-modern_chinese_history		✓		23	acc
Ceval-valid-ideological_and_moral_cultivation		✓		19	acc
Ceval-valid-logic		✓		22	acc
Ceval-valid-law		✓		24	acc
Ceval-valid-chinese_language_and_literature		✓		23	acc
Ceval-valid-art_studies		✓		33	acc
Ceval-valid-professional_tour_guide		✓		29	acc
Ceval-valid-legal_professional		✓		23	acc
Ceval-valid-high_school_chinese		✓		19	acc
Ceval-valid-high_school_history		✓		20	acc
Ceval-valid-middle_school_history		✓		22	acc
Ceval-valid-civil_servant		✓		47	acc
Ceval-valid-sports_science		✓		19	acc
Ceval-valid-plant_protection		✓		22	acc
Ceval-valid-basic_medicine		✓		19	acc
Ceval-valid-clinical_medicine		✓		22	acc
Ceval-valid-urban_and_rural_planner		✓		46	acc
Ceval-valid-accountant		✓		49	acc
Ceval-valid-fire_engineer		✓		31	acc
Ceval-valid-environmental_impact_assessment_engineer		✓		31	acc
Ceval-valid-tax_accountant		✓		49	acc
Ceval-valid-physician		✓		49	acc