| 0 |
glue/mnli |
glue |
mnli |
|
glue___mnli |
Classification |
| 1 |
glue/qnli |
glue |
qnli |
|
glue___qnli |
Classification |
| 2 |
glue/rte |
glue |
rte |
|
glue___rte |
Classification |
| 3 |
glue/wnli |
glue |
wnli |
|
glue___wnli |
Classification |
| 4 |
glue/mrpc |
glue |
mrpc |
|
glue___mrpc |
Classification |
| 5 |
glue/qqp |
glue |
qqp |
|
glue___qqp |
Classification |
| 6 |
glue/stsb |
glue |
stsb |
|
glue___stsb |
Classification |
| 7 |
super_glue/boolq |
super_glue |
boolq |
|
super_glue___boolq |
Classification |
| 8 |
super_glue/cb |
super_glue |
cb |
|
super_glue___cb |
Classification |
| 9 |
super_glue/multirc |
super_glue |
multirc |
|
super_glue___multirc |
Classification |
| 10 |
super_glue/wic |
super_glue |
wic |
|
super_glue___wic |
Classification |
| 11 |
super_glue/axg |
super_glue |
axg |
|
super_glue___axg |
Classification |
| 12 |
anli/a1 |
anli |
|
a1 |
anli__a1 |
Classification |
| 13 |
anli/a2 |
anli |
|
a2 |
anli__a2 |
Classification |
| 14 |
anli/a3 |
anli |
|
a3 |
anli__a3 |
Classification |
| 15 |
babi_nli/basic-coreference |
tasksource/babi_nli |
basic-coreference |
|
babi_nli |
Classification |
| 16 |
babi_nli/single-supporting-fact |
tasksource/babi_nli |
single-supporting-fact |
|
babi_nli |
Classification |
| 17 |
babi_nli/yes-no-questions |
tasksource/babi_nli |
yes-no-questions |
|
babi_nli |
Classification |
| 18 |
babi_nli/compound-coreference |
tasksource/babi_nli |
compound-coreference |
|
babi_nli |
Classification |
| 19 |
babi_nli/size-reasoning |
tasksource/babi_nli |
size-reasoning |
|
babi_nli |
Classification |
| 20 |
babi_nli/lists-sets |
tasksource/babi_nli |
lists-sets |
|
babi_nli |
Classification |
| 21 |
babi_nli/positional-reasoning |
tasksource/babi_nli |
positional-reasoning |
|
babi_nli |
Classification |
| 22 |
babi_nli/indefinite-knowledge |
tasksource/babi_nli |
indefinite-knowledge |
|
babi_nli |
Classification |
| 23 |
babi_nli/path-finding |
tasksource/babi_nli |
path-finding |
|
babi_nli |
Classification |
| 24 |
babi_nli/two-supporting-facts |
tasksource/babi_nli |
two-supporting-facts |
|
babi_nli |
Classification |
| 25 |
babi_nli/basic-induction |
tasksource/babi_nli |
basic-induction |
|
babi_nli |
Classification |
| 26 |
babi_nli/three-arg-relations |
tasksource/babi_nli |
three-arg-relations |
|
babi_nli |
Classification |
| 27 |
babi_nli/time-reasoning |
tasksource/babi_nli |
time-reasoning |
|
babi_nli |
Classification |
| 28 |
babi_nli/two-arg-relations |
tasksource/babi_nli |
two-arg-relations |
|
babi_nli |
Classification |
| 29 |
babi_nli/three-supporting-facts |
tasksource/babi_nli |
three-supporting-facts |
|
babi_nli |
Classification |
| 30 |
babi_nli/conjunction |
tasksource/babi_nli |
conjunction |
|
babi_nli |
Classification |
| 31 |
babi_nli/basic-deduction |
tasksource/babi_nli |
basic-deduction |
|
babi_nli |
Classification |
| 32 |
babi_nli/counting |
tasksource/babi_nli |
counting |
|
babi_nli |
Classification |
| 33 |
babi_nli/simple-negation |
tasksource/babi_nli |
simple-negation |
|
babi_nli |
Classification |
| 34 |
sick/label |
sick |
|
label |
sick__label |
Classification |
| 35 |
sick/relatedness |
sick |
|
relatedness |
sick__relatedness |
Classification |
| 36 |
sick/entailment_AB |
sick |
|
entailment_AB |
sick__entailment_AB |
Classification |
| 37 |
snli |
snli |
|
|
snli |
Classification |
| 38 |
scitail/snli_format |
scitail |
snli_format |
|
scitail |
Classification |
| 39 |
hans |
hans |
|
|
hans |
Classification |
| 40 |
WANLI |
alisawuffles/WANLI |
|
|
wanli |
Classification |
| 41 |
recast/recast_puns |
tasksource/recast |
recast_puns |
|
recast_nli |
Classification |
| 42 |
recast/recast_factuality |
tasksource/recast |
recast_factuality |
|
recast_nli |
Classification |
| 43 |
recast/recast_verbnet |
tasksource/recast |
recast_verbnet |
|
recast_nli |
Classification |
| 44 |
recast/recast_sentiment |
tasksource/recast |
recast_sentiment |
|
recast_nli |
Classification |
| 45 |
recast/recast_kg_relations |
tasksource/recast |
recast_kg_relations |
|
recast_nli |
Classification |
| 46 |
recast/recast_verbcorner |
tasksource/recast |
recast_verbcorner |
|
recast_nli |
Classification |
| 47 |
recast/recast_ner |
tasksource/recast |
recast_ner |
|
recast_nli |
Classification |
| 48 |
recast/recast_megaveridicality |
tasksource/recast |
recast_megaveridicality |
|
recast_nli |
Classification |
| 49 |
probability_words_nli/reasoning_2hop |
sileod/probability_words_nli |
reasoning_2hop |
|
probability_words_nli |
Classification |
| 50 |
probability_words_nli/reasoning_1hop |
sileod/probability_words_nli |
reasoning_1hop |
|
probability_words_nli |
Classification |
| 51 |
probability_words_nli/usnli |
sileod/probability_words_nli |
usnli |
|
probability_words_nli |
Classification |
| 52 |
nan-nli/joey234--nan-nli |
joey234/nan-nli |
joey234--nan-nli |
|
nan_nli |
Classification |
| 53 |
nli_fever |
pietrolesci/nli_fever |
|
|
nli_fever |
Classification |
| 54 |
breaking_nli |
pietrolesci/breaking_nli |
|
|
breaking_nli |
Classification |
| 55 |
conj_nli |
pietrolesci/conj_nli |
|
|
conj_nli |
Classification |
| 56 |
fracas |
pietrolesci/fracas |
|
|
fracas |
Classification |
| 57 |
dialogue_nli |
pietrolesci/dialogue_nli |
|
|
dialogue_nli |
Classification |
| 58 |
mpe |
pietrolesci/mpe |
|
|
mpe_nli |
Classification |
| 59 |
dnc |
pietrolesci/dnc |
|
|
dnc_nli |
Classification |
| 60 |
recast_white/fnplus |
pietrolesci/recast_white |
|
fnplus |
recast_white__fnplus |
Classification |
| 61 |
recast_white/sprl |
pietrolesci/recast_white |
|
sprl |
recast_white__sprl |
Classification |
| 62 |
recast_white/dpr |
pietrolesci/recast_white |
|
dpr |
recast_white__dpr |
Classification |
| 63 |
joci |
pietrolesci/joci |
|
|
joci |
Classification |
| 64 |
robust_nli/IS_CS |
pietrolesci/robust_nli |
|
IS_CS |
robust_nli__IS_CS |
Classification |
| 65 |
robust_nli/LI_LI |
pietrolesci/robust_nli |
|
LI_LI |
robust_nli__LI_LI |
Classification |
| 66 |
robust_nli/ST_WO |
pietrolesci/robust_nli |
|
ST_WO |
robust_nli__ST_WO |
Classification |
| 67 |
robust_nli/PI_SP |
pietrolesci/robust_nli |
|
PI_SP |
robust_nli__PI_SP |
Classification |
| 68 |
robust_nli/PI_CD |
pietrolesci/robust_nli |
|
PI_CD |
robust_nli__PI_CD |
Classification |
| 69 |
robust_nli/ST_SE |
pietrolesci/robust_nli |
|
ST_SE |
robust_nli__ST_SE |
Classification |
| 70 |
robust_nli/ST_NE |
pietrolesci/robust_nli |
|
ST_NE |
robust_nli__ST_NE |
Classification |
| 71 |
robust_nli/ST_LM |
pietrolesci/robust_nli |
|
ST_LM |
robust_nli__ST_LM |
Classification |
| 72 |
robust_nli_is_sd |
pietrolesci/robust_nli_is_sd |
|
|
robust_nli_is_sd |
Classification |
| 73 |
robust_nli_li_ts |
pietrolesci/robust_nli_li_ts |
|
|
robust_nli_li_ts |
Classification |
| 74 |
gen_debiased_nli/snli_seq_z |
pietrolesci/gen_debiased_nli |
|
snli_seq_z |
gen_debiased_nli__snli_seq_z |
Classification |
| 75 |
gen_debiased_nli/snli_z_aug |
pietrolesci/gen_debiased_nli |
|
snli_z_aug |
gen_debiased_nli__snli_z_aug |
Classification |
| 76 |
gen_debiased_nli/snli_par_z |
pietrolesci/gen_debiased_nli |
|
snli_par_z |
gen_debiased_nli__snli_par_z |
Classification |
| 77 |
gen_debiased_nli/mnli_par_z |
pietrolesci/gen_debiased_nli |
|
mnli_par_z |
gen_debiased_nli__mnli_par_z |
Classification |
| 78 |
gen_debiased_nli/mnli_z_aug |
pietrolesci/gen_debiased_nli |
|
mnli_z_aug |
gen_debiased_nli__mnli_z_aug |
Classification |
| 79 |
gen_debiased_nli/mnli_seq_z |
pietrolesci/gen_debiased_nli |
|
mnli_seq_z |
gen_debiased_nli__mnli_seq_z |
Classification |
| 80 |
add_one_rte |
pietrolesci/add_one_rte |
|
|
add_one_rte |
Classification |
| 81 |
imppres/presupposition_cleft_uniqueness/presupposition |
tasksource/imppres |
presupposition_cleft_uniqueness |
presupposition |
imppres__presupposition |
Classification |
| 82 |
imppres/presupposition_cleft_existence/presupposition |
tasksource/imppres |
presupposition_cleft_existence |
presupposition |
imppres__presupposition |
Classification |
| 83 |
imppres/presupposition_possessed_definites_uniqueness/presupposition |
tasksource/imppres |
presupposition_possessed_definites_uniqueness |
presupposition |
imppres__presupposition |
Classification |
| 84 |
imppres/presupposition_possessed_definites_existence/presupposition |
tasksource/imppres |
presupposition_possessed_definites_existence |
presupposition |
imppres__presupposition |
Classification |
| 85 |
imppres/presupposition_only_presupposition/presupposition |
tasksource/imppres |
presupposition_only_presupposition |
presupposition |
imppres__presupposition |
Classification |
| 86 |
imppres/presupposition_all_n_presupposition/presupposition |
tasksource/imppres |
presupposition_all_n_presupposition |
presupposition |
imppres__presupposition |
Classification |
| 87 |
imppres/presupposition_both_presupposition/presupposition |
tasksource/imppres |
presupposition_both_presupposition |
presupposition |
imppres__presupposition |
Classification |
| 88 |
imppres/presupposition_change_of_state/presupposition |
tasksource/imppres |
presupposition_change_of_state |
presupposition |
imppres__presupposition |
Classification |
| 89 |
imppres/presupposition_question_presupposition/presupposition |
tasksource/imppres |
presupposition_question_presupposition |
presupposition |
imppres__presupposition |
Classification |
| 90 |
imppres/implicature_connectives/prag |
tasksource/imppres |
implicature_connectives |
prag |
imppres__prag |
Classification |
| 91 |
imppres/implicature_modals/prag |
tasksource/imppres |
implicature_modals |
prag |
imppres__prag |
Classification |
| 92 |
imppres/implicature_numerals_2_3/prag |
tasksource/imppres |
implicature_numerals_2_3 |
prag |
imppres__prag |
Classification |
| 93 |
imppres/implicature_quantifiers/prag |
tasksource/imppres |
implicature_quantifiers |
prag |
imppres__prag |
Classification |
| 94 |
imppres/implicature_numerals_10_100/prag |
tasksource/imppres |
implicature_numerals_10_100 |
prag |
imppres__prag |
Classification |
| 95 |
imppres/implicature_gradable_adjective/prag |
tasksource/imppres |
implicature_gradable_adjective |
prag |
imppres__prag |
Classification |
| 96 |
imppres/implicature_gradable_verb/prag |
tasksource/imppres |
implicature_gradable_verb |
prag |
imppres__prag |
Classification |
| 97 |
imppres/implicature_gradable_adjective/log |
tasksource/imppres |
implicature_gradable_adjective |
log |
imppres__log |
Classification |
| 98 |
imppres/implicature_modals/log |
tasksource/imppres |
implicature_modals |
log |
imppres__log |
Classification |
| 99 |
imppres/implicature_connectives/log |
tasksource/imppres |
implicature_connectives |
log |
imppres__log |
Classification |
| 100 |
imppres/implicature_numerals_2_3/log |
tasksource/imppres |
implicature_numerals_2_3 |
log |
imppres__log |
Classification |
| 101 |
imppres/implicature_numerals_10_100/log |
tasksource/imppres |
implicature_numerals_10_100 |
log |
imppres__log |
Classification |
| 102 |
imppres/implicature_gradable_verb/log |
tasksource/imppres |
implicature_gradable_verb |
log |
imppres__log |
Classification |
| 103 |
imppres/implicature_quantifiers/log |
tasksource/imppres |
implicature_quantifiers |
log |
imppres__log |
Classification |
| 104 |
hlgd |
hlgd |
|
|
hlgd |
Classification |
| 105 |
paws/labeled_final |
paws |
labeled_final |
|
paws___labeled_final |
Classification |
| 106 |
paws/labeled_swap |
paws |
labeled_swap |
|
paws___labeled_swap |
Classification |
| 107 |
medical_questions_pairs |
medical_questions_pairs |
|
|
medical_questions_pairs |
Classification |
| 108 |
conll2003/pos_tags |
conll2003 |
|
pos_tags |
conll2003__pos_tags |
TokenClassification |
| 109 |
conll2003/chunk_tags |
conll2003 |
|
chunk_tags |
conll2003__chunk_tags |
TokenClassification |
| 110 |
conll2003/ner_tags |
conll2003 |
|
ner_tags |
conll2003__ner_tags |
TokenClassification |
| 111 |
model-written-evals |
Anthropic/model-written-evals |
|
|
model_written_evals |
MultipleChoice |
| 112 |
truthful_qa/multiple_choice |
truthful_qa |
multiple_choice |
|
truthful_qa___multiple_choice |
MultipleChoice |
| 113 |
fig-qa |
nightingal3/fig-qa |
|
|
fig_qa |
MultipleChoice |
| 114 |
bigbench/misconceptions |
tasksource/bigbench |
misconceptions |
|
bigbench |
MultipleChoice |
| 115 |
bigbench/social_support |
tasksource/bigbench |
social_support |
|
bigbench |
MultipleChoice |
| 116 |
bigbench/dark_humor_detection |
tasksource/bigbench |
dark_humor_detection |
|
bigbench |
MultipleChoice |
| 117 |
bigbench/general_knowledge |
tasksource/bigbench |
general_knowledge |
|
bigbench |
MultipleChoice |
| 118 |
bigbench/code_line_description |
tasksource/bigbench |
code_line_description |
|
bigbench |
MultipleChoice |
| 119 |
bigbench/unit_interpretation |
tasksource/bigbench |
unit_interpretation |
|
bigbench |
MultipleChoice |
| 120 |
bigbench/date_understanding |
tasksource/bigbench |
date_understanding |
|
bigbench |
MultipleChoice |
| 121 |
bigbench/tracking_shuffled_objects |
tasksource/bigbench |
tracking_shuffled_objects |
|
bigbench |
MultipleChoice |
| 122 |
bigbench/formal_fallacies_syllogisms_negation |
tasksource/bigbench |
formal_fallacies_syllogisms_negation |
|
bigbench |
MultipleChoice |
| 123 |
bigbench/nonsense_words_grammar |
tasksource/bigbench |
nonsense_words_grammar |
|
bigbench |
MultipleChoice |
| 124 |
bigbench/anachronisms |
tasksource/bigbench |
anachronisms |
|
bigbench |
MultipleChoice |
| 125 |
bigbench/discourse_marker_prediction |
tasksource/bigbench |
discourse_marker_prediction |
|
bigbench |
MultipleChoice |
| 126 |
bigbench/metaphor_understanding |
tasksource/bigbench |
metaphor_understanding |
|
bigbench |
MultipleChoice |
| 127 |
bigbench/logical_args |
tasksource/bigbench |
logical_args |
|
bigbench |
MultipleChoice |
| 128 |
bigbench/mnist_ascii |
tasksource/bigbench |
mnist_ascii |
|
bigbench |
MultipleChoice |
| 129 |
bigbench/sentence_ambiguity |
tasksource/bigbench |
sentence_ambiguity |
|
bigbench |
MultipleChoice |
| 130 |
bigbench/presuppositions_as_nli |
tasksource/bigbench |
presuppositions_as_nli |
|
bigbench |
MultipleChoice |
| 131 |
bigbench/gre_reading_comprehension |
tasksource/bigbench |
gre_reading_comprehension |
|
bigbench |
MultipleChoice |
| 132 |
bigbench/emojis_emotion_prediction |
tasksource/bigbench |
emojis_emotion_prediction |
|
bigbench |
MultipleChoice |
| 133 |
bigbench/play_dialog_same_or_different |
tasksource/bigbench |
play_dialog_same_or_different |
|
bigbench |
MultipleChoice |
| 134 |
bigbench/geometric_shapes |
tasksource/bigbench |
geometric_shapes |
|
bigbench |
MultipleChoice |
| 135 |
bigbench/authorship_verification |
tasksource/bigbench |
authorship_verification |
|
bigbench |
MultipleChoice |
| 136 |
bigbench/logical_deduction |
tasksource/bigbench |
logical_deduction |
|
bigbench |
MultipleChoice |
| 137 |
bigbench/logical_sequence |
tasksource/bigbench |
logical_sequence |
|
bigbench |
MultipleChoice |
| 138 |
bigbench/strategyqa |
tasksource/bigbench |
strategyqa |
|
bigbench |
MultipleChoice |
| 139 |
bigbench/fantasy_reasoning |
tasksource/bigbench |
fantasy_reasoning |
|
bigbench |
MultipleChoice |
| 140 |
bigbench/timedial |
tasksource/bigbench |
timedial |
|
bigbench |
MultipleChoice |
| 141 |
bigbench/emoji_movie |
tasksource/bigbench |
emoji_movie |
|
bigbench |
MultipleChoice |
| 142 |
bigbench/entailed_polarity |
tasksource/bigbench |
entailed_polarity |
|
bigbench |
MultipleChoice |
| 143 |
bigbench/fact_checker |
tasksource/bigbench |
fact_checker |
|
bigbench |
MultipleChoice |
| 144 |
bigbench/movie_dialog_same_or_different |
tasksource/bigbench |
movie_dialog_same_or_different |
|
bigbench |
MultipleChoice |
| 145 |
bigbench/moral_permissibility |
tasksource/bigbench |
moral_permissibility |
|
bigbench |
MultipleChoice |
| 146 |
bigbench/human_organs_senses |
tasksource/bigbench |
human_organs_senses |
|
bigbench |
MultipleChoice |
| 147 |
bigbench/analogical_similarity |
tasksource/bigbench |
analogical_similarity |
|
bigbench |
MultipleChoice |
| 148 |
bigbench/social_iqa |
tasksource/bigbench |
social_iqa |
|
bigbench |
MultipleChoice |
| 149 |
bigbench/analytic_entailment |
tasksource/bigbench |
analytic_entailment |
|
bigbench |
MultipleChoice |
| 150 |
bigbench/penguins_in_a_table |
tasksource/bigbench |
penguins_in_a_table |
|
bigbench |
MultipleChoice |
| 151 |
bigbench/intent_recognition |
tasksource/bigbench |
intent_recognition |
|
bigbench |
MultipleChoice |
| 152 |
bigbench/ruin_names |
tasksource/bigbench |
ruin_names |
|
bigbench |
MultipleChoice |
| 153 |
bigbench/checkmate_in_one |
tasksource/bigbench |
checkmate_in_one |
|
bigbench |
MultipleChoice |
| 154 |
bigbench/metaphor_boolean |
tasksource/bigbench |
metaphor_boolean |
|
bigbench |
MultipleChoice |
| 155 |
bigbench/cs_algorithms |
tasksource/bigbench |
cs_algorithms |
|
bigbench |
MultipleChoice |
| 156 |
bigbench/cause_and_effect |
tasksource/bigbench |
cause_and_effect |
|
bigbench |
MultipleChoice |
| 157 |
bigbench/disambiguation_qa |
tasksource/bigbench |
disambiguation_qa |
|
bigbench |
MultipleChoice |
| 158 |
bigbench/undo_permutation |
tasksource/bigbench |
undo_permutation |
|
bigbench |
MultipleChoice |
| 159 |
bigbench/odd_one_out |
tasksource/bigbench |
odd_one_out |
|
bigbench |
MultipleChoice |
| 160 |
bigbench/international_phonetic_alphabet_nli |
tasksource/bigbench |
international_phonetic_alphabet_nli |
|
bigbench |
MultipleChoice |
| 161 |
bigbench/goal_step_wikihow |
tasksource/bigbench |
goal_step_wikihow |
|
bigbench |
MultipleChoice |
| 162 |
bigbench/implicatures |
tasksource/bigbench |
implicatures |
|
bigbench |
MultipleChoice |
| 163 |
bigbench/physical_intuition |
tasksource/bigbench |
physical_intuition |
|
bigbench |
MultipleChoice |
| 164 |
bigbench/real_or_fake_text |
tasksource/bigbench |
real_or_fake_text |
|
bigbench |
MultipleChoice |
| 165 |
bigbench/reasoning_about_colored_objects |
tasksource/bigbench |
reasoning_about_colored_objects |
|
bigbench |
MultipleChoice |
| 166 |
bigbench/temporal_sequences |
tasksource/bigbench |
temporal_sequences |
|
bigbench |
MultipleChoice |
| 167 |
bigbench/sports_understanding |
tasksource/bigbench |
sports_understanding |
|
bigbench |
MultipleChoice |
| 168 |
bigbench/mathematical_induction |
tasksource/bigbench |
mathematical_induction |
|
bigbench |
MultipleChoice |
| 169 |
bigbench/snarks |
tasksource/bigbench |
snarks |
|
bigbench |
MultipleChoice |
| 170 |
bigbench/identify_odd_metaphor |
tasksource/bigbench |
identify_odd_metaphor |
|
bigbench |
MultipleChoice |
| 171 |
bigbench/logical_fallacy_detection |
tasksource/bigbench |
logical_fallacy_detection |
|
bigbench |
MultipleChoice |
| 172 |
bigbench/understanding_fables |
tasksource/bigbench |
understanding_fables |
|
bigbench |
MultipleChoice |
| 173 |
bigbench/conceptual_combinations |
tasksource/bigbench |
conceptual_combinations |
|
bigbench |
MultipleChoice |
| 174 |
bigbench/key_value_maps |
tasksource/bigbench |
key_value_maps |
|
bigbench |
MultipleChoice |
| 175 |
bigbench/logic_grid_puzzle |
tasksource/bigbench |
logic_grid_puzzle |
|
bigbench |
MultipleChoice |
| 176 |
bigbench/salient_translation_error_detection |
tasksource/bigbench |
salient_translation_error_detection |
|
bigbench |
MultipleChoice |
| 177 |
bigbench/vitaminc_fact_verification |
tasksource/bigbench |
vitaminc_fact_verification |
|
bigbench |
MultipleChoice |
| 178 |
bigbench/epistemic_reasoning |
tasksource/bigbench |
epistemic_reasoning |
|
bigbench |
MultipleChoice |
| 179 |
bigbench/abstract_narrative_understanding |
tasksource/bigbench |
abstract_narrative_understanding |
|
bigbench |
MultipleChoice |
| 180 |
bigbench/simple_ethical_questions |
tasksource/bigbench |
simple_ethical_questions |
|
bigbench |
MultipleChoice |
| 181 |
bigbench/suicide_risk |
tasksource/bigbench |
suicide_risk |
|
bigbench |
MultipleChoice |
| 182 |
bigbench/question_selection |
tasksource/bigbench |
question_selection |
|
bigbench |
MultipleChoice |
| 183 |
bigbench/winowhy |
tasksource/bigbench |
winowhy |
|
bigbench |
MultipleChoice |
| 184 |
bigbench/crash_blossom |
tasksource/bigbench |
crash_blossom |
|
bigbench |
MultipleChoice |
| 185 |
bigbench/riddle_sense |
tasksource/bigbench |
riddle_sense |
|
bigbench |
MultipleChoice |
| 186 |
bigbench/color |
tasksource/bigbench |
color |
|
bigbench |
MultipleChoice |
| 187 |
bigbench/strange_stories |
tasksource/bigbench |
strange_stories |
|
bigbench |
MultipleChoice |
| 188 |
bigbench/arithmetic |
tasksource/bigbench |
arithmetic |
|
bigbench |
MultipleChoice |
| 189 |
bigbench/irony_identification |
tasksource/bigbench |
irony_identification |
|
bigbench |
MultipleChoice |
| 190 |
bigbench/implicit_relations |
tasksource/bigbench |
implicit_relations |
|
bigbench |
MultipleChoice |
| 191 |
bigbench/causal_judgment |
tasksource/bigbench |
causal_judgment |
|
bigbench |
MultipleChoice |
| 192 |
bigbench/figure_of_speech_detection |
tasksource/bigbench |
figure_of_speech_detection |
|
bigbench |
MultipleChoice |
| 193 |
bigbench/hindu_knowledge |
tasksource/bigbench |
hindu_knowledge |
|
bigbench |
MultipleChoice |
| 194 |
bigbench/evaluating_information_essentiality |
tasksource/bigbench |
evaluating_information_essentiality |
|
bigbench |
MultipleChoice |
| 195 |
bigbench/similarities_abstraction |
tasksource/bigbench |
similarities_abstraction |
|
bigbench |
MultipleChoice |
| 196 |
bigbench/bbq_lite_json |
tasksource/bigbench |
bbq_lite_json |
|
bigbench |
MultipleChoice |
| 197 |
bigbench/novel_concepts |
tasksource/bigbench |
novel_concepts |
|
bigbench |
MultipleChoice |
| 198 |
bigbench/english_proverbs |
tasksource/bigbench |
english_proverbs |
|
bigbench |
MultipleChoice |
| 199 |
bigbench/known_unknowns |
tasksource/bigbench |
known_unknowns |
|
bigbench |
MultipleChoice |
| 200 |
bigbench/navigate |
tasksource/bigbench |
navigate |
|
bigbench |
MultipleChoice |
| 201 |
bigbench/phrase_relatedness |
tasksource/bigbench |
phrase_relatedness |
|
bigbench |
MultipleChoice |
| 202 |
bigbench/contextual_parametric_knowledge_conflicts |
tasksource/bigbench |
contextual_parametric_knowledge_conflicts |
|
bigbench |
MultipleChoice |
| 203 |
bigbench/symbol_interpretation |
tasksource/bigbench |
symbol_interpretation |
|
bigbench |
MultipleChoice |
| 204 |
bigbench/hhh_alignment |
tasksource/bigbench |
hhh_alignment |
|
bigbench |
MultipleChoice |
| 205 |
bigbench/hyperbaton |
tasksource/bigbench |
hyperbaton |
|
bigbench |
MultipleChoice |
| 206 |
bigbench/empirical_judgments |
tasksource/bigbench |
empirical_judgments |
|
bigbench |
MultipleChoice |
| 207 |
bigbench/identify_math_theorems |
tasksource/bigbench |
identify_math_theorems |
|
bigbench |
MultipleChoice |
| 208 |
bigbench/crass_ai |
tasksource/bigbench |
crass_ai |
|
bigbench |
MultipleChoice |
| 209 |
bigbench/elementary_math_qa |
tasksource/bigbench |
elementary_math_qa |
|
bigbench |
MultipleChoice |
| 210 |
bigbench/movie_recommendation |
tasksource/bigbench |
movie_recommendation |
|
bigbench |
MultipleChoice |
| 211 |
bigbench/dyck_languages |
tasksource/bigbench |
dyck_languages |
|
bigbench |
MultipleChoice |
| 212 |
bigbench/cifar10_classification |
tasksource/bigbench |
cifar10_classification |
|
bigbench |
MultipleChoice |
| 213 |
bigbench/physics |
tasksource/bigbench |
physics |
|
bigbench |
MultipleChoice |
| 214 |
blimp/sentential_subject_island |
blimp |
sentential_subject_island |
|
blimp_hard |
MultipleChoice |
| 215 |
blimp/tough_vs_raising_1 |
blimp |
tough_vs_raising_1 |
|
blimp_hard |
MultipleChoice |
| 216 |
blimp/wh_vs_that_with_gap |
blimp |
wh_vs_that_with_gap |
|
blimp_hard |
MultipleChoice |
| 217 |
blimp/wh_questions_object_gap |
blimp |
wh_questions_object_gap |
|
blimp_hard |
MultipleChoice |
| 218 |
blimp/principle_A_c_command |
blimp |
principle_A_c_command |
|
blimp_hard |
MultipleChoice |
| 219 |
blimp/existential_there_quantifiers_2 |
blimp |
existential_there_quantifiers_2 |
|
blimp_hard |
MultipleChoice |
| 220 |
blimp/principle_A_domain_2 |
blimp |
principle_A_domain_2 |
|
blimp_hard |
MultipleChoice |
| 221 |
blimp/left_branch_island_echo_question |
blimp |
left_branch_island_echo_question |
|
blimp_hard |
MultipleChoice |
| 222 |
blimp/npi_present_2 |
blimp |
npi_present_2 |
|
blimp_hard |
MultipleChoice |
| 223 |
blimp/complex_NP_island |
blimp |
complex_NP_island |
|
blimp_hard |
MultipleChoice |
| 224 |
blimp/animate_subject_passive |
blimp |
animate_subject_passive |
|
blimp_hard |
MultipleChoice |
| 225 |
blimp/coordinate_structure_constraint_complex_left_branch |
blimp |
coordinate_structure_constraint_complex_left_branch |
|
blimp_hard |
MultipleChoice |
| 226 |
blimp/coordinate_structure_constraint_object_extraction |
blimp |
coordinate_structure_constraint_object_extraction |
|
blimp_hard |
MultipleChoice |
| 227 |
blimp/superlative_quantifiers_1 |
blimp |
superlative_quantifiers_1 |
|
blimp_hard |
MultipleChoice |
| 228 |
blimp/drop_argument |
blimp |
drop_argument |
|
blimp_hard |
MultipleChoice |
| 229 |
blimp/sentential_negation_npi_scope |
blimp |
sentential_negation_npi_scope |
|
blimp_hard |
MultipleChoice |
| 230 |
blimp/npi_present_1 |
blimp |
npi_present_1 |
|
blimp_hard |
MultipleChoice |
| 231 |
blimp/matrix_question_npi_licensor_present |
blimp |
matrix_question_npi_licensor_present |
|
blimp_hard |
MultipleChoice |
| 232 |
blimp/inchoative |
blimp |
inchoative |
|
blimp_hard |
MultipleChoice |
| 233 |
blimp/wh_vs_that_with_gap_long_distance |
blimp |
wh_vs_that_with_gap_long_distance |
|
blimp_hard |
MultipleChoice |
| 234 |
blimp/principle_A_reconstruction |
blimp |
principle_A_reconstruction |
|
blimp_hard |
MultipleChoice |
| 235 |
blimp/wh_questions_subject_gap_long_distance |
blimp |
wh_questions_subject_gap_long_distance |
|
blimp_hard |
MultipleChoice |
| 236 |
cos_e/v1.0 |
cos_e |
v1.0 |
|
cos_e |
MultipleChoice |
| 237 |
cosmos_qa |
cosmos_qa |
|
|
cosmos_qa |
MultipleChoice |
| 238 |
dream |
dream |
|
|
dream |
MultipleChoice |
| 239 |
openbookqa |
openbookqa |
|
|
openbookqa |
MultipleChoice |
| 240 |
qasc |
qasc |
|
|
qasc |
MultipleChoice |
| 241 |
quartz |
quartz |
|
|
quartz |
MultipleChoice |
| 242 |
quail |
quail |
|
|
quail |
MultipleChoice |
| 243 |
head_qa/en |
head_qa |
en |
|
head_qa___en |
MultipleChoice |
| 244 |
sciq |
sciq |
|
|
sciq |
MultipleChoice |
| 245 |
social_i_qa |
social_i_qa |
|
|
social_i_qa |
MultipleChoice |
| 246 |
wiki_hop/original |
wiki_hop |
original |
|
wiki_hop___original |
MultipleChoice |
| 247 |
wiqa |
wiqa |
|
|
wiqa |
MultipleChoice |
| 248 |
piqa |
piqa |
|
|
piqa |
MultipleChoice |
| 249 |
hellaswag |
hellaswag |
|
|
hellaswag |
MultipleChoice |
| 250 |
super_glue/copa |
super_glue |
copa |
|
super_glue___copa |
MultipleChoice |
| 251 |
balanced-copa |
pkavumba/balanced-copa |
|
|
balanced_copa |
MultipleChoice |
| 252 |
e-CARE |
12ml/e-CARE |
|
|
e_care |
MultipleChoice |
| 253 |
art |
art |
|
|
art |
MultipleChoice |
| 254 |
mmlu/prehistory |
tasksource/mmlu |
prehistory |
|
mmlu |
MultipleChoice |
| 255 |
mmlu/clinical_knowledge |
tasksource/mmlu |
clinical_knowledge |
|
mmlu |
MultipleChoice |
| 256 |
mmlu/college_biology |
tasksource/mmlu |
college_biology |
|
mmlu |
MultipleChoice |
| 257 |
mmlu/college_chemistry |
tasksource/mmlu |
college_chemistry |
|
mmlu |
MultipleChoice |
| 258 |
mmlu/college_computer_science |
tasksource/mmlu |
college_computer_science |
|
mmlu |
MultipleChoice |
| 259 |
mmlu/medical_genetics |
tasksource/mmlu |
medical_genetics |
|
mmlu |
MultipleChoice |
| 260 |
mmlu/miscellaneous |
tasksource/mmlu |
miscellaneous |
|
mmlu |
MultipleChoice |
| 261 |
mmlu/moral_disputes |
tasksource/mmlu |
moral_disputes |
|
mmlu |
MultipleChoice |
| 262 |
mmlu/moral_scenarios |
tasksource/mmlu |
moral_scenarios |
|
mmlu |
MultipleChoice |
| 263 |
mmlu/high_school_physics |
tasksource/mmlu |
high_school_physics |
|
mmlu |
MultipleChoice |
| 264 |
mmlu/high_school_psychology |
tasksource/mmlu |
high_school_psychology |
|
mmlu |
MultipleChoice |
| 265 |
mmlu/high_school_statistics |
tasksource/mmlu |
high_school_statistics |
|
mmlu |
MultipleChoice |
| 266 |
mmlu/high_school_us_history |
tasksource/mmlu |
high_school_us_history |
|
mmlu |
MultipleChoice |
| 267 |
mmlu/college_mathematics |
tasksource/mmlu |
college_mathematics |
|
mmlu |
MultipleChoice |
| 268 |
mmlu/college_medicine |
tasksource/mmlu |
college_medicine |
|
mmlu |
MultipleChoice |
| 269 |
mmlu/college_physics |
tasksource/mmlu |
college_physics |
|
mmlu |
MultipleChoice |
| 270 |
mmlu/business_ethics |
tasksource/mmlu |
business_ethics |
|
mmlu |
MultipleChoice |
| 271 |
mmlu/professional_law |
tasksource/mmlu |
professional_law |
|
mmlu |
MultipleChoice |
| 272 |
mmlu/professional_medicine |
tasksource/mmlu |
professional_medicine |
|
mmlu |
MultipleChoice |
| 273 |
mmlu/professional_psychology |
tasksource/mmlu |
professional_psychology |
|
mmlu |
MultipleChoice |
| 274 |
mmlu/public_relations |
tasksource/mmlu |
public_relations |
|
mmlu |
MultipleChoice |
| 275 |
mmlu/logical_fallacies |
tasksource/mmlu |
logical_fallacies |
|
mmlu |
MultipleChoice |
| 276 |
mmlu/machine_learning |
tasksource/mmlu |
machine_learning |
|
mmlu |
MultipleChoice |
| 277 |
mmlu/management |
tasksource/mmlu |
management |
|
mmlu |
MultipleChoice |
| 278 |
mmlu/marketing |
tasksource/mmlu |
marketing |
|
mmlu |
MultipleChoice |
| 279 |
mmlu/sociology |
tasksource/mmlu |
sociology |
|
mmlu |
MultipleChoice |
| 280 |
mmlu/us_foreign_policy |
tasksource/mmlu |
us_foreign_policy |
|
mmlu |
MultipleChoice |
| 281 |
mmlu/virology |
tasksource/mmlu |
virology |
|
mmlu |
MultipleChoice |
| 282 |
mmlu/world_religions |
tasksource/mmlu |
world_religions |
|
mmlu |
MultipleChoice |
| 283 |
mmlu/nutrition |
tasksource/mmlu |
nutrition |
|
mmlu |
MultipleChoice |
| 284 |
mmlu/philosophy |
tasksource/mmlu |
philosophy |
|
mmlu |
MultipleChoice |
| 285 |
mmlu/high_school_biology |
tasksource/mmlu |
high_school_biology |
|
mmlu |
MultipleChoice |
| 286 |
mmlu/jurisprudence |
tasksource/mmlu |
jurisprudence |
|
mmlu |
MultipleChoice |
| 287 |
mmlu/international_law |
tasksource/mmlu |
international_law |
|
mmlu |
MultipleChoice |
| 288 |
mmlu/anatomy |
tasksource/mmlu |
anatomy |
|
mmlu |
MultipleChoice |
| 289 |
mmlu/abstract_algebra |
tasksource/mmlu |
abstract_algebra |
|
mmlu |
MultipleChoice |
| 290 |
mmlu/security_studies |
tasksource/mmlu |
security_studies |
|
mmlu |
MultipleChoice |
| 291 |
mmlu/astronomy |
tasksource/mmlu |
astronomy |
|
mmlu |
MultipleChoice |
| 292 |
mmlu/professional_accounting |
tasksource/mmlu |
professional_accounting |
|
mmlu |
MultipleChoice |
| 293 |
mmlu/high_school_world_history |
tasksource/mmlu |
high_school_world_history |
|
mmlu |
MultipleChoice |
| 294 |
mmlu/human_aging |
tasksource/mmlu |
human_aging |
|
mmlu |
MultipleChoice |
| 295 |
mmlu/human_sexuality |
tasksource/mmlu |
human_sexuality |
|
mmlu |
MultipleChoice |
| 296 |
mmlu/high_school_chemistry |
tasksource/mmlu |
high_school_chemistry |
|
mmlu |
MultipleChoice |
| 297 |
mmlu/high_school_computer_science |
tasksource/mmlu |
high_school_computer_science |
|
mmlu |
MultipleChoice |
| 298 |
mmlu/high_school_european_history |
tasksource/mmlu |
high_school_european_history |
|
mmlu |
MultipleChoice |
| 299 |
mmlu/high_school_geography |
tasksource/mmlu |
high_school_geography |
|
mmlu |
MultipleChoice |
| 300 |
mmlu/high_school_government_and_politics |
tasksource/mmlu |
high_school_government_and_politics |
|
mmlu |
MultipleChoice |
| 301 |
mmlu/high_school_macroeconomics |
tasksource/mmlu |
high_school_macroeconomics |
|
mmlu |
MultipleChoice |
| 302 |
mmlu/high_school_mathematics |
tasksource/mmlu |
high_school_mathematics |
|
mmlu |
MultipleChoice |
| 303 |
mmlu/high_school_microeconomics |
tasksource/mmlu |
high_school_microeconomics |
|
mmlu |
MultipleChoice |
| 304 |
mmlu/computer_security |
tasksource/mmlu |
computer_security |
|
mmlu |
MultipleChoice |
| 305 |
mmlu/conceptual_physics |
tasksource/mmlu |
conceptual_physics |
|
mmlu |
MultipleChoice |
| 306 |
mmlu/econometrics |
tasksource/mmlu |
econometrics |
|
mmlu |
MultipleChoice |
| 307 |
mmlu/electrical_engineering |
tasksource/mmlu |
electrical_engineering |
|
mmlu |
MultipleChoice |
| 308 |
mmlu/elementary_mathematics |
tasksource/mmlu |
elementary_mathematics |
|
mmlu |
MultipleChoice |
| 309 |
mmlu/formal_logic |
tasksource/mmlu |
formal_logic |
|
mmlu |
MultipleChoice |
| 310 |
mmlu/global_facts |
tasksource/mmlu |
global_facts |
|
mmlu |
MultipleChoice |
| 311 |
winogrande/winogrande_xl |
winogrande |
winogrande_xl |
|
winogrande |
MultipleChoice |
| 312 |
codah/codah |
codah |
codah |
|
codah |
MultipleChoice |
| 313 |
ai2_arc/ARC-Easy/challenge |
ai2_arc |
ARC-Easy |
challenge |
ai2_arc__challenge |
MultipleChoice |
| 314 |
ai2_arc/ARC-Challenge/challenge |
ai2_arc |
ARC-Challenge |
challenge |
ai2_arc__challenge |
MultipleChoice |
| 315 |
definite_pronoun_resolution |
definite_pronoun_resolution |
|
|
definite_pronoun_resolution |
MultipleChoice |
| 316 |
swag/regular |
swag |
regular |
|
swag___regular |
MultipleChoice |
| 317 |
math_qa |
math_qa |
|
|
math_qa |
MultipleChoice |
| 318 |
glue/cola |
glue |
cola |
|
glue___cola |
Classification |
| 319 |
glue/sst2 |
glue |
sst2 |
|
glue___sst2 |
Classification |
| 320 |
utilitarianism |
metaeval/utilitarianism |
|
|
utilitarianism |
Classification |
| 321 |
amazon_counterfactual/en |
mteb/amazon_counterfactual |
en |
|
amazon_counterfactual |
Classification |
| 322 |
insincere-questions |
SetFit/insincere-questions |
|
|
insincere_questions |
Classification |
| 323 |
toxic_conversations |
SetFit/toxic_conversations |
|
|
toxic_conversations |
Classification |
| 324 |
TuringBench |
turingbench/TuringBench |
|
|
turingbench |
Classification |
| 325 |
trec |
trec |
|
|
trec |
Classification |
| 326 |
vitaminc/tals--vitaminc |
tals/vitaminc |
tals--vitaminc |
|
tals_vitaminc |
Classification |
| 327 |
hope_edi/english |
hope_edi |
english |
|
hope_edi |
Classification |
| 328 |
rumoureval_2019/RumourEval2019 |
strombergnlp/rumoureval_2019 |
RumourEval2019 |
|
rumoureval_2019 |
Classification |
| 329 |
ethos/binary |
ethos |
binary |
|
ethos___binary |
Classification |
| 330 |
ethos/multilabel |
ethos |
multilabel |
|
ethos___multilabel |
Classification |
| 331 |
tweet_eval/emoji |
tweet_eval |
emoji |
|
tweet_eval |
Classification |
| 332 |
tweet_eval/offensive |
tweet_eval |
offensive |
|
tweet_eval |
Classification |
| 333 |
tweet_eval/emotion |
tweet_eval |
emotion |
|
tweet_eval |
Classification |
| 334 |
tweet_eval/hate |
tweet_eval |
hate |
|
tweet_eval |
Classification |
| 335 |
tweet_eval/irony |
tweet_eval |
irony |
|
tweet_eval |
Classification |
| 336 |
tweet_eval/sentiment |
tweet_eval |
sentiment |
|
tweet_eval |
Classification |
| 337 |
tweet_eval/stance_abortion |
tweet_eval |
stance_abortion |
|
tweet_eval_abortion |
Classification |
| 338 |
tweet_eval/stance_atheism |
tweet_eval |
stance_atheism |
|
tweet_eval_atheism |
Classification |
| 339 |
tweet_eval/stance_climate |
tweet_eval |
stance_climate |
|
tweet_eval_climate |
Classification |
| 340 |
tweet_eval/stance_feminist |
tweet_eval |
stance_feminist |
|
tweet_eval_feminist |
Classification |
| 341 |
tweet_eval/stance_hillary |
tweet_eval |
stance_hillary |
|
tweet_eval_hillary |
Classification |
| 342 |
discovery/discovery |
discovery |
discovery |
|
discovery |
Classification |
| 343 |
pragmeval/emobank-dominance |
pragmeval |
emobank-dominance |
|
pragmeval_1 |
Classification |
| 344 |
pragmeval/emobank-valence |
pragmeval |
emobank-valence |
|
pragmeval_1 |
Classification |
| 345 |
pragmeval/squinky-formality |
pragmeval |
squinky-formality |
|
pragmeval_1 |
Classification |
| 346 |
pragmeval/squinky-implicature |
pragmeval |
squinky-implicature |
|
pragmeval_1 |
Classification |
| 347 |
pragmeval/squinky-informativeness |
pragmeval |
squinky-informativeness |
|
pragmeval_1 |
Classification |
| 348 |
pragmeval/switchboard |
pragmeval |
switchboard |
|
pragmeval_1 |
Classification |
| 349 |
pragmeval/mrda |
pragmeval |
mrda |
|
pragmeval_1 |
Classification |
| 350 |
pragmeval/verifiability |
pragmeval |
verifiability |
|
pragmeval_1 |
Classification |
| 351 |
pragmeval/emobank-arousal |
pragmeval |
emobank-arousal |
|
pragmeval_1 |
Classification |
| 352 |
pragmeval/persuasiveness-specificity |
pragmeval |
persuasiveness-specificity |
|
pragmeval_2 |
Classification |
| 353 |
pragmeval/persuasiveness-strength |
pragmeval |
persuasiveness-strength |
|
pragmeval_2 |
Classification |
| 354 |
pragmeval/persuasiveness-relevance |
pragmeval |
persuasiveness-relevance |
|
pragmeval_2 |
Classification |
| 355 |
pragmeval/stac |
pragmeval |
stac |
|
pragmeval_2 |
Classification |
| 356 |
pragmeval/pdtb |
pragmeval |
pdtb |
|
pragmeval_2 |
Classification |
| 357 |
pragmeval/gum |
pragmeval |
gum |
|
pragmeval_2 |
Classification |
| 358 |
pragmeval/emergent |
pragmeval |
emergent |
|
pragmeval_2 |
Classification |
| 359 |
pragmeval/persuasiveness-claimtype |
pragmeval |
persuasiveness-claimtype |
|
pragmeval_2 |
Classification |
| 360 |
pragmeval/sarcasm |
pragmeval |
sarcasm |
|
pragmeval_2 |
Classification |
| 361 |
pragmeval/persuasiveness-premisetype |
pragmeval |
persuasiveness-premisetype |
|
pragmeval_2 |
Classification |
| 362 |
pragmeval/persuasiveness-eloquence |
pragmeval |
persuasiveness-eloquence |
|
pragmeval_2 |
Classification |
| 363 |
silicone/meld_s |
silicone |
meld_s |
|
silicone |
Classification |
| 364 |
silicone/maptask |
silicone |
maptask |
|
silicone |
Classification |
| 365 |
silicone/dyda_e |
silicone |
dyda_e |
|
silicone |
Classification |
| 366 |
silicone/dyda_da |
silicone |
dyda_da |
|
silicone |
Classification |
| 367 |
silicone/iemocap |
silicone |
iemocap |
|
silicone |
Classification |
| 368 |
silicone/oasis |
silicone |
oasis |
|
silicone |
Classification |
| 369 |
silicone/sem |
silicone |
sem |
|
silicone |
Classification |
| 370 |
silicone/meld_e |
silicone |
meld_e |
|
silicone |
Classification |
| 371 |
lex_glue/eurlex |
lex_glue |
eurlex |
|
lex_glue___eurlex |
Classification |
| 372 |
lex_glue/scotus |
lex_glue |
scotus |
|
lex_glue___scotus |
Classification |
| 373 |
lex_glue/ledgar |
lex_glue |
ledgar |
|
lex_glue___ledgar |
Classification |
| 374 |
lex_glue/unfair_tos |
lex_glue |
unfair_tos |
|
lex_glue___unfair_tos |
Classification |
| 375 |
lex_glue/case_hold |
lex_glue |
case_hold |
|
lex_glue___case_hold |
MultipleChoice |
| 376 |
language-identification |
papluca/language-identification |
|
|
language_identification |
Classification |
| 377 |
imdb |
imdb |
|
|
imdb |
Classification |
| 378 |
rotten_tomatoes |
rotten_tomatoes |
|
|
rotten_tomatoes |
Classification |
| 379 |
ag_news |
ag_news |
|
|
ag_news |
Classification |
| 380 |
yelp_review_full/yelp_review_full |
yelp_review_full |
yelp_review_full |
|
yelp_review_full |
Classification |
| 381 |
financial_phrasebank/sentences_allagree |
financial_phrasebank |
sentences_allagree |
|
financial_phrasebank |
Classification |
| 382 |
poem_sentiment |
poem_sentiment |
|
|
poem_sentiment |
Classification |
| 383 |
dbpedia_14/dbpedia_14 |
dbpedia_14 |
dbpedia_14 |
|
dbpedia_14 |
Classification |
| 384 |
amazon_polarity/amazon_polarity |
amazon_polarity |
amazon_polarity |
|
amazon_polarity |
Classification |
| 385 |
app_reviews |
app_reviews |
|
|
app_reviews |
Classification |
| 386 |
hate_speech18 |
hate_speech18 |
|
|
hate_speech18 |
Classification |
| 387 |
sms_spam |
sms_spam |
|
|
sms_spam |
Classification |
| 388 |
humicroedit/subtask-1 |
humicroedit |
subtask-1 |
|
humicroedit___subtask_1 |
Classification |
| 389 |
humicroedit/subtask-2 |
humicroedit |
subtask-2 |
|
humicroedit___subtask_2 |
Classification |
| 390 |
snips_built_in_intents |
snips_built_in_intents |
|
|
snips_built_in_intents |
Classification |
| 391 |
hate_speech_offensive |
hate_speech_offensive |
|
|
hate_speech_offensive |
Classification |
| 392 |
yahoo_answers_topics |
yahoo_answers_topics |
|
|
yahoo_answers_topics |
Classification |
| 393 |
stackoverflow-questions |
pacovaldez/stackoverflow-questions |
|
|
stackoverflow_questions |
Classification |
| 394 |
hyperpartisan_news |
zapsdcn/hyperpartisan_news |
|
|
hyperpartisan_news |
Classification |
| 395 |
sciie |
zapsdcn/sciie |
|
|
scierc |
Classification |
| 396 |
citation_intent |
zapsdcn/citation_intent |
|
|
citation_intent |
Classification |
| 397 |
go_emotions/simplified |
go_emotions |
simplified |
|
go_emotions___simplified |
Classification |
| 398 |
scicite |
allenai/scicite |
|
|
scicite |
Classification |
| 399 |
liar |
liar |
|
|
liar |
Classification |
| 400 |
lexical_relation_classification/ROOT09 |
relbert/lexical_relation_classification |
ROOT09 |
|
relbert_lexical_relation_classification |
Classification |
| 401 |
lexical_relation_classification/CogALexV |
relbert/lexical_relation_classification |
CogALexV |
|
relbert_lexical_relation_classification |
Classification |
| 402 |
lexical_relation_classification/EVALution |
relbert/lexical_relation_classification |
EVALution |
|
relbert_lexical_relation_classification |
Classification |
| 403 |
lexical_relation_classification/K&H+N |
relbert/lexical_relation_classification |
K&H+N |
|
relbert_lexical_relation_classification |
Classification |
| 404 |
lexical_relation_classification/BLESS |
relbert/lexical_relation_classification |
BLESS |
|
relbert_lexical_relation_classification |
Classification |
| 405 |
linguisticprobing/sentence_length |
tasksource/linguisticprobing |
sentence_length |
|
linguisticprobing |
Classification |
| 406 |
linguisticprobing/top_constituents |
tasksource/linguisticprobing |
top_constituents |
|
linguisticprobing |
Classification |
| 407 |
linguisticprobing/past_present |
tasksource/linguisticprobing |
past_present |
|
linguisticprobing |
Classification |
| 408 |
linguisticprobing/obj_number |
tasksource/linguisticprobing |
obj_number |
|
linguisticprobing |
Classification |
| 409 |
linguisticprobing/subj_number |
tasksource/linguisticprobing |
subj_number |
|
linguisticprobing |
Classification |
| 410 |
linguisticprobing/tree_depth |
tasksource/linguisticprobing |
tree_depth |
|
linguisticprobing |
Classification |
| 411 |
linguisticprobing/bigram_shift |
tasksource/linguisticprobing |
bigram_shift |
|
linguisticprobing |
Classification |
| 412 |
linguisticprobing/coordination_inversion |
tasksource/linguisticprobing |
coordination_inversion |
|
linguisticprobing |
Classification |
| 413 |
linguisticprobing/odd_man_out |
tasksource/linguisticprobing |
odd_man_out |
|
linguisticprobing |
Classification |
| 414 |
crowdflower/political-media-bias |
tasksource/crowdflower |
political-media-bias |
|
crowdflower |
Classification |
| 415 |
crowdflower/corporate-messaging |
tasksource/crowdflower |
corporate-messaging |
|
crowdflower |
Classification |
| 416 |
crowdflower/political-media-audience |
tasksource/crowdflower |
political-media-audience |
|
crowdflower |
Classification |
| 417 |
crowdflower/economic-news |
tasksource/crowdflower |
economic-news |
|
crowdflower |
Classification |
| 418 |
crowdflower/tweet_global_warming |
tasksource/crowdflower |
tweet_global_warming |
|
crowdflower |
Classification |
| 419 |
crowdflower/sentiment_nuclear_power |
tasksource/crowdflower |
sentiment_nuclear_power |
|
crowdflower |
Classification |
| 420 |
crowdflower/text_emotion |
tasksource/crowdflower |
text_emotion |
|
crowdflower |
Classification |
| 421 |
crowdflower/political-media-message |
tasksource/crowdflower |
political-media-message |
|
crowdflower |
Classification |
| 422 |
crowdflower/airline-sentiment |
tasksource/crowdflower |
airline-sentiment |
|
crowdflower |
Classification |
| 423 |
ethics/commonsense |
metaeval/ethics |
commonsense |
|
ethics___commonsense |
Classification |
| 424 |
ethics/deontology |
metaeval/ethics |
deontology |
|
ethics___deontology |
Classification |
| 425 |
ethics/justice |
metaeval/ethics |
justice |
|
ethics___justice |
Classification |
| 426 |
ethics/virtue |
metaeval/ethics |
virtue |
|
ethics___virtue |
Classification |
| 427 |
emo/emo2019 |
emo |
emo2019 |
|
emo |
Classification |
| 428 |
google_wellformed_query |
google_wellformed_query |
|
|
google_wellformed_query |
Classification |
| 429 |
tweets_hate_speech_detection |
tweets_hate_speech_detection |
|
|
tweets_hate_speech_detection |
Classification |
| 430 |
has_part |
has_part |
|
|
has_part |
Classification |
| 431 |
wnut_17/wnut_17 |
wnut_17 |
wnut_17 |
|
wnut_17 |
TokenClassification |
| 432 |
ncbi_disease/ncbi_disease |
ncbi_disease |
ncbi_disease |
|
ncbi_disease |
TokenClassification |
| 433 |
acronym_identification |
acronym_identification |
|
|
acronym_identification |
TokenClassification |
| 434 |
jnlpba/jnlpba |
jnlpba |
jnlpba |
|
jnlpba |
TokenClassification |
| 435 |
ontonotes_english/SpeedOfMagic--ontonotes_english |
SpeedOfMagic/ontonotes_english |
SpeedOfMagic--ontonotes_english |
|
SpeedOfMagic_ontonotes_english |
TokenClassification |
| 436 |
blog_authorship_corpus/gender |
blog_authorship_corpus |
|
gender |
blog_authorship_corpus__gender |
Classification |
| 437 |
blog_authorship_corpus/age |
blog_authorship_corpus |
|
age |
blog_authorship_corpus__age |
Classification |
| 438 |
blog_authorship_corpus/job |
blog_authorship_corpus |
|
job |
blog_authorship_corpus__job |
Classification |
| 439 |
open_question_type |
launch/open_question_type |
|
|
launch_open_question_type |
Classification |
| 440 |
health_fact |
health_fact |
|
|
health_fact |
Classification |
| 441 |
commonsense_qa |
commonsense_qa |
|
|
commonsense_qa |
MultipleChoice |
| 442 |
mc_taco |
mc_taco |
|
|
mc_taco |
Classification |
| 443 |
ade_corpus_v2/Ade_corpus_v2_classification |
ade_corpus_v2 |
Ade_corpus_v2_classification |
|
ade_corpus_v2___Ade_corpus_v2_classification |
Classification |
| 444 |
discosense |
prajjwal1/discosense |
|
|
discosense |
MultipleChoice |
| 445 |
circa |
circa |
|
|
circa |
Classification |
| 446 |
phrase_similarity |
PiC/phrase_similarity |
|
|
phrase_similarity |
Classification |
| 447 |
scientific-exaggeration-detection |
copenlu/scientific-exaggeration-detection |
|
|
exaggeration_detection |
Classification |
| 448 |
quarel |
quarel |
|
|
quarel |
Classification |
| 449 |
fever-evidence-related/mwong--fever-related |
mwong/fever-evidence-related |
mwong--fever-related |
|
mwong_fever_evidence_related |
Classification |
| 450 |
numer_sense |
numer_sense |
|
|
numer_sense |
Classification |
| 451 |
dynasent/dynabench.dynasent.r1.all/r1 |
dynabench/dynasent |
dynabench.dynasent.r1.all |
r1 |
dynasent__r1 |
Classification |
| 452 |
dynasent/dynabench.dynasent.r2.all/r2 |
dynabench/dynasent |
dynabench.dynasent.r2.all |
r2 |
dynasent__r2 |
Classification |
| 453 |
Sarcasm_News_Headline |
raquiba/Sarcasm_News_Headline |
|
|
sarcasm_news |
Classification |
| 454 |
sem_eval_2010_task_8 |
sem_eval_2010_task_8 |
|
|
sem_eval_2010_task_8 |
Classification |
| 455 |
auditor_review/demo-org--auditor_review |
demo-org/auditor_review |
demo-org--auditor_review |
|
demo_org_auditor_review |
Classification |
| 456 |
medmcqa |
medmcqa |
|
|
medmcqa |
MultipleChoice |
| 457 |
Dynasent_Disagreement |
RuyuanWan/Dynasent_Disagreement |
|
|
dynasent_disagreement |
Classification |
| 458 |
Politeness_Disagreement |
RuyuanWan/Politeness_Disagreement |
|
|
politeness_disagreement |
Classification |
| 459 |
SBIC_Disagreement |
RuyuanWan/SBIC_Disagreement |
|
|
sbic_disagreement |
Classification |
| 460 |
SChem_Disagreement |
RuyuanWan/SChem_Disagreement |
|
|
schem_disagreement |
Classification |
| 461 |
Dilemmas_Disagreement |
RuyuanWan/Dilemmas_Disagreement |
|
|
dilemmas_disagreement |
Classification |
| 462 |
logiqa |
lucasmccabe/logiqa |
|
|
logiqa |
MultipleChoice |
| 463 |
wiki_qa |
wiki_qa |
|
|
wiki_qa |
Classification |
| 464 |
cycic_classification |
tasksource/cycic_classification |
|
|
cycic_classification |
Classification |
| 465 |
cycic_multiplechoice |
tasksource/cycic_multiplechoice |
|
|
cycic_mc |
MultipleChoice |
| 466 |
sts-companion |
tasksource/sts-companion |
|
|
sts_companion |
Classification |
| 467 |
commonsense_qa_2.0 |
tasksource/commonsense_qa_2.0 |
|
|
commonsense_qa_2 |
Classification |
| 468 |
lingnli |
tasksource/lingnli |
|
|
ling_nli |
Classification |
| 469 |
monotonicity-entailment |
tasksource/monotonicity-entailment |
|
|
monotonicity_entailment |
Classification |
| 470 |
arct |
tasksource/arct |
|
|
arct |
MultipleChoice |
| 471 |
scinli |
tasksource/scinli |
|
|
scinli |
Classification |
| 472 |
naturallogic |
tasksource/naturallogic |
|
|
naturallogic |
Classification |
| 473 |
onestop_qa |
onestop_qa |
|
|
onestop_qa |
MultipleChoice |
| 474 |
moral_stories/full |
demelin/moral_stories |
full |
|
moral_stories |
MultipleChoice |
| 475 |
prost |
corypaik/prost |
|
|
prost |
MultipleChoice |
| 476 |
dynahate |
aps/dynahate |
|
|
dyna_hate |
Classification |
| 477 |
syntactic-augmentation-nli |
metaeval/syntactic-augmentation-nli |
|
|
syntactic_augmentation_nli |
Classification |
| 478 |
autotnli |
tasksource/autotnli |
|
|
autotnli |
Classification |
| 479 |
CONDAQA |
lasha-nlp/CONDAQA |
|
|
conqada |
Classification |
| 480 |
webgpt_comparisons |
openai/webgpt_comparisons |
|
|
webgbpt_comparisons |
MultipleChoice |
| 481 |
synthetic-instruct-gptj-pairwise |
Dahoas/synthetic-instruct-gptj-pairwise |
|
|
synthetic_instruct |
MultipleChoice |
| 482 |
scruples |
metaeval/scruples |
|
|
scruples |
Classification |
| 483 |
wouldyourather |
metaeval/wouldyourather |
|
|
wouldyourather |
MultipleChoice |
| 484 |
defeasible-nli/snli |
metaeval/defeasible-nli |
snli |
|
defeasible_nli |
Classification |
| 485 |
defeasible-nli/atomic |
metaeval/defeasible-nli |
atomic |
|
defeasible_nli |
Classification |
| 486 |
help-nli |
tasksource/help-nli |
|
|
help_nli |
Classification |
| 487 |
nli-veridicality-transitivity |
metaeval/nli-veridicality-transitivity |
|
|
nli_veridicality_transitivity |
Classification |
| 488 |
lonli |
tasksource/lonli |
|
|
lonli |
Classification |
| 489 |
dadc-limit-nli |
tasksource/dadc-limit-nli |
|
|
dadc_limit |
Classification |
| 490 |
FLUTE |
ColumbiaNLP/FLUTE |
|
|
flute |
Classification |
| 491 |
strategy-qa |
tasksource/strategy-qa |
|
|
strategy_qa |
Classification |
| 492 |
summarize_from_feedback/comparisons |
openai/summarize_from_feedback |
comparisons |
|
summarize_from_feedback |
MultipleChoice |
| 493 |
folio |
tasksource/folio |
|
|
folio |
Classification |
| 494 |
tomi-nli |
tasksource/tomi-nli |
|
|
tomi_nli |
Classification |
| 495 |
avicenna |
tasksource/avicenna |
|
|
avicenna |
Classification |
| 496 |
SHP |
stanfordnlp/SHP |
|
|
shp |
MultipleChoice |
| 497 |
MedQA-USMLE-4-options-hf |
GBaker/MedQA-USMLE-4-options-hf |
|
|
medqa_usmle |
MultipleChoice |
| 498 |
wikimedqa/medwiki |
sileod/wikimedqa |
medwiki |
|
wikimedqa |
MultipleChoice |
| 499 |
cicero |
declare-lab/cicero |
|
|
cicero |
MultipleChoice |
| 500 |
CREAK |
amydeng2000/CREAK |
|
|
creak |
Classification |
| 501 |
mutual |
tasksource/mutual |
|
|
mutual |
MultipleChoice |
| 502 |
NeQA |
inverse-scaling/NeQA |
|
|
neqa |
MultipleChoice |
| 503 |
quote-repetition |
inverse-scaling/quote-repetition |
|
|
quote_repetition |
MultipleChoice |
| 504 |
redefine-math |
inverse-scaling/redefine-math |
|
|
redefine_math |
MultipleChoice |
| 505 |
puzzte |
tasksource/puzzte |
|
|
puzzte |
Classification |
| 506 |
implicatures |
tasksource/implicatures |
|
|
implicatures |
MultipleChoice |
| 507 |
race/middle |
race |
middle |
|
race |
MultipleChoice |
| 508 |
race/high |
race |
high |
|
race |
MultipleChoice |
| 509 |
race-c |
tasksource/race-c |
|
|
race_c |
MultipleChoice |
| 510 |
spartqa-yn |
tasksource/spartqa-yn |
|
|
spartqa_yn |
Classification |
| 511 |
spartqa-mchoice |
tasksource/spartqa-mchoice |
|
|
spartqa_mc |
MultipleChoice |
| 512 |
temporal-nli |
tasksource/temporal-nli |
|
|
temporal_nli |
Classification |
| 513 |
riddle_sense |
riddle_sense |
|
|
riddle_sense |
MultipleChoice |
| 514 |
clcd-english |
tasksource/clcd-english |
|
|
clcd |
Classification |
| 515 |
twentyquestions |
maximedb/twentyquestions |
|
|
twentyquestions |
Classification |
| 516 |
reclor |
metaeval/reclor |
|
|
reclor |
MultipleChoice |
| 517 |
counterfactually-augmented-imdb |
tasksource/counterfactually-augmented-imdb |
|
|
c_aug_imdb |
Classification |
| 518 |
counterfactually-augmented-snli |
tasksource/counterfactually-augmented-snli |
|
|
c_aug_snli |
Classification |
| 519 |
cnli |
metaeval/cnli |
|
|
cnli |
Classification |
| 520 |
boolq-natural-perturbations |
tasksource/boolq-natural-perturbations |
|
|
perturbed_boolq |
Classification |
| 521 |
acceptability-prediction |
metaeval/acceptability-prediction |
|
|
graded_acceptability |
Classification |
| 522 |
equate |
metaeval/equate |
|
|
equate |
Classification |
| 523 |
ScienceQA_text_only |
tasksource/ScienceQA_text_only |
|
|
science_qa |
MultipleChoice |
| 524 |
ekar_english |
Jiangjie/ekar_english |
|
|
ekar |
MultipleChoice |
| 525 |
implicit-hate-stg1 |
tasksource/implicit-hate-stg1 |
|
|
implicit_hate |
Classification |
| 526 |
chaos-mnli-ambiguity |
metaeval/chaos-mnli-ambiguity |
|
|
nli_unambiguity |
Classification |
| 527 |
headline_cause/en_simple |
IlyaGusev/headline_cause |
en_simple |
|
headline_cause |
Classification |
| 528 |
logiqa-2.0-nli |
tasksource/logiqa-2.0-nli |
|
|
logiqa_2 |
Classification |
| 529 |
oasst2_dense_flat/quality |
tasksource/oasst2_dense_flat |
|
quality |
oasst1__quality |
Classification |
| 530 |
oasst2_dense_flat/toxicity |
tasksource/oasst2_dense_flat |
|
toxicity |
oasst1__toxicity |
Classification |
| 531 |
oasst2_dense_flat/helpfulness |
tasksource/oasst2_dense_flat |
|
helpfulness |
oasst1__helpfulness |
Classification |
| 532 |
mindgames |
sileod/mindgames |
|
|
mindgames |
Classification |
| 533 |
universal_dependencies/en_partut/deprel |
universal_dependencies |
en_partut |
deprel |
udep__deprel |
TokenClassification |
| 534 |
universal_dependencies/en_ewt/deprel |
universal_dependencies |
en_ewt |
deprel |
udep__deprel |
TokenClassification |
| 535 |
universal_dependencies/en_gum/deprel |
universal_dependencies |
en_gum |
deprel |
udep__deprel |
TokenClassification |
| 536 |
universal_dependencies/en_lines/deprel |
universal_dependencies |
en_lines |
deprel |
udep__deprel |
TokenClassification |
| 537 |
ambient |
metaeval/ambient |
|
|
ambient |
Classification |
| 538 |
path-naturalness-prediction |
metaeval/path-naturalness-prediction |
|
|
path_naturalness |
MultipleChoice |
| 539 |
civil_comments/toxicity |
civil_comments |
|
toxicity |
civil_comments__toxicity |
Classification |
| 540 |
civil_comments/severe_toxicity |
civil_comments |
|
severe_toxicity |
civil_comments__severe_toxicity |
Classification |
| 541 |
civil_comments/obscene |
civil_comments |
|
obscene |
civil_comments__obscene |
Classification |
| 542 |
civil_comments/threat |
civil_comments |
|
threat |
civil_comments__threat |
Classification |
| 543 |
civil_comments/insult |
civil_comments |
|
insult |
civil_comments__insult |
Classification |
| 544 |
civil_comments/identity_attack |
civil_comments |
|
identity_attack |
civil_comments__identity_attack |
Classification |
| 545 |
civil_comments/sexual_explicit |
civil_comments |
|
sexual_explicit |
civil_comments__sexual_explicit |
Classification |
| 546 |
cloth |
AndyChiang/cloth |
|
|
cloth |
MultipleChoice |
| 547 |
dgen |
AndyChiang/dgen |
|
|
dgen |
MultipleChoice |
| 548 |
I2D2 |
tasksource/I2D2 |
|
|
i2d2 |
Classification |
| 549 |
args_me |
webis/args_me |
|
|
arg_me |
Classification |
| 550 |
Touche23-ValueEval |
webis/Touche23-ValueEval |
|
|
valueeval_stance |
Classification |
| 551 |
starcon |
tasksource/starcon |
|
|
starcon |
Classification |
| 552 |
banking77 |
PolyAI/banking77 |
|
|
banking77 |
Classification |
| 553 |
ConTRoL-nli |
tasksource/ConTRoL-nli |
|
|
control |
Classification |
| 554 |
tracie |
tasksource/tracie |
|
|
tracie |
Classification |
| 555 |
sherliic |
tasksource/sherliic |
|
|
sherliic |
Classification |
| 556 |
sen-making/1 |
tasksource/sen-making |
|
1 |
sen_making__1 |
MultipleChoice |
| 557 |
sen-making/2 |
tasksource/sen-making |
|
2 |
sen_making__2 |
MultipleChoice |
| 558 |
winowhy |
tasksource/winowhy |
|
|
winowhy |
Classification |
| 559 |
robustLR |
tasksource/robustLR |
|
|
robustLR |
Classification |
| 560 |
v1/gen_train234_test2to10 |
CLUTRR/v1 |
gen_train234_test2to10 |
|
cluttr |
Classification |
| 561 |
logical-fallacy |
tasksource/logical-fallacy |
|
|
logical_fallacy |
Classification |
| 562 |
parade |
tasksource/parade |
|
|
parade |
Classification |
| 563 |
cladder |
tasksource/cladder |
|
|
cladder |
Classification |
| 564 |
subjectivity |
tasksource/subjectivity |
|
|
subjectivity |
Classification |
| 565 |
MOH |
tasksource/MOH |
|
|
moh |
Classification |
| 566 |
VUAC |
tasksource/VUAC |
|
|
vuac |
Classification |
| 567 |
TroFi |
tasksource/TroFi |
|
|
trofi |
Classification |
| 568 |
sharc_modified/mod |
sharc_modified |
mod |
|
sharc_classification |
Classification |
| 569 |
conceptrules_v2 |
tasksource/conceptrules_v2 |
|
|
conceptrules_v2 |
Classification |
| 570 |
disrpt/eng.dep.scidtb.rels |
metaeval/disrpt |
eng.dep.scidtb.rels |
|
scidtb |
Classification |
| 571 |
conll2000 |
conll2000 |
|
|
chunking |
TokenClassification |
| 572 |
few-nerd/supervised |
DFKI-SLT/few-nerd |
supervised |
|
few_nerd |
TokenClassification |
| 573 |
finer-139 |
nlpaueb/finer-139 |
|
|
finer |
TokenClassification |
| 574 |
zero-shot-label-nli |
tasksource/zero-shot-label-nli |
|
|
label_nli |
Classification |
| 575 |
com2sense |
tasksource/com2sense |
|
|
com2sense |
Classification |
| 576 |
scone |
tasksource/scone |
|
|
scone |
Classification |
| 577 |
winodict |
tasksource/winodict |
|
|
winodict |
MultipleChoice |
| 578 |
fool-me-twice |
tasksource/fool-me-twice |
|
|
fool_me_twice |
Classification |
| 579 |
monli |
tasksource/monli |
|
|
monli |
Classification |
| 580 |
corr2cause |
tasksource/corr2cause |
|
|
causality |
Classification |
| 581 |
lsat_qa/all |
lighteval/lsat_qa |
all |
|
lsat |
MultipleChoice |
| 582 |
apt |
tasksource/apt |
|
|
apt |
Classification |
| 583 |
twitter-financial-news-sentiment |
zeroshot/twitter-financial-news-sentiment |
|
|
financial_sentiment |
Classification |
| 584 |
icl-symbol-tuning-instruct |
tasksource/icl-symbol-tuning-instruct |
|
|
icl |
Classification |
| 585 |
SpaceNLI |
tasksource/SpaceNLI |
|
|
space_nli |
Classification |
| 586 |
propsegment/nli |
sihaochen/propsegment |
nli |
|
propsegment |
Classification |
| 587 |
HatemojiBuild |
HannahRoseKirk/HatemojiBuild |
|
|
hatemoji |
Classification |
| 588 |
regset |
tasksource/regset |
|
|
regset |
Classification |
| 589 |
esci |
tasksource/esci |
|
|
esci |
Classification |
| 590 |
chatbot_arena_conversations |
lmsys/chatbot_arena_conversations |
|
|
chatbot_arena |
MultipleChoice |
| 591 |
dnd_style_intents |
neurae/dnd_style_intents |
|
|
dnd_intent |
Classification |
| 592 |
FLD.v2/default |
hitachi-nlp/FLD.v2 |
default |
|
fld |
Classification |
| 593 |
FLD.v2/star |
hitachi-nlp/FLD.v2 |
star |
|
flds |
Classification |
| 594 |
SDOH-NLI |
tasksource/SDOH-NLI |
|
|
sdoh_nli |
Classification |
| 595 |
scifact_entailment |
allenai/scifact_entailment |
|
|
scifact_entailment |
Classification |
| 596 |
feasibilityQA |
tasksource/feasibilityQA |
|
|
feasibilityQA |
Classification |
| 597 |
simple_pair |
tasksource/simple_pair |
|
|
simple_pair |
Classification |
| 598 |
AdjectiveScaleProbe-nli |
tasksource/AdjectiveScaleProbe-nli |
|
|
adjective_scale_probe |
Classification |
| 599 |
resnli |
tasksource/resnli |
|
|
repectively_nli |
Classification |
| 600 |
SpaRTUN |
tasksource/SpaRTUN |
|
|
spartun |
MultipleChoice |
| 601 |
ReSQ |
tasksource/ReSQ |
|
|
resq |
MultipleChoice |
| 602 |
semantic_fragments_nli |
tasksource/semantic_fragments_nli |
|
|
semantic_fragments_nli |
Classification |
| 603 |
dataset_train_nli |
MoritzLaurer/dataset_train_nli |
|
|
moritz_zs_nli |
Classification |
| 604 |
stepgame |
tasksource/stepgame |
|
|
stepgame |
Classification |
| 605 |
nlgraph |
tasksource/nlgraph |
|
|
nlgraph |
Classification |
| 606 |
oasst2_pairwise_rlhf_reward |
tasksource/oasst2_pairwise_rlhf_reward |
|
|
oasst_rlhf |
MultipleChoice |
| 607 |
hh-rlhf/helpful-rejection-sampled |
tasksource/hh-rlhf |
helpful-rejection-sampled |
|
anthropic_rlhf_helpfulness |
MultipleChoice |
| 608 |
hh-rlhf/helpful-online |
tasksource/hh-rlhf |
helpful-online |
|
anthropic_rlhf_helpfulness |
MultipleChoice |
| 609 |
hh-rlhf/helpful-base |
tasksource/hh-rlhf |
helpful-base |
|
anthropic_rlhf_helpfulness |
MultipleChoice |
| 610 |
hh-rlhf/harmless-base |
tasksource/hh-rlhf |
harmless-base |
|
anthropic_rlhf_harmless |
MultipleChoice |
| 611 |
ruletaker |
tasksource/ruletaker |
|
|
ruletaker |
Classification |
| 612 |
PARARULE-Plus |
qbao775/PARARULE-Plus |
|
|
para_rules |
Classification |
| 613 |
proofwriter |
tasksource/proofwriter |
|
|
proofwriter_deduction |
Classification |
| 614 |
logical-entailment |
tasksource/logical-entailment |
|
|
logical_entailment |
Classification |
| 615 |
nope |
tasksource/nope |
|
|
nope |
Classification |
| 616 |
LogicNLI |
tasksource/LogicNLI |
|
|
logicNLI |
Classification |
| 617 |
contract-nli/contractnli_a |
kiddothe2b/contract-nli |
contractnli_a |
|
contract_nli |
Classification |
| 618 |
nli4ct_semeval2024 |
AshtonIsNotHere/nli4ct_semeval2024 |
|
|
nli4ct |
Classification |
| 619 |
lsat-ar |
tasksource/lsat-ar |
|
|
lsat_ar |
MultipleChoice |
| 620 |
lsat-rc |
tasksource/lsat-rc |
|
|
lsat_rc |
MultipleChoice |
| 621 |
biosift-nli |
AshtonIsNotHere/biosift-nli |
|
|
biosift_nli |
Classification |
| 622 |
brainteasers/SP |
tasksource/brainteasers |
SP |
|
brainteasers |
MultipleChoice |
| 623 |
brainteasers/WP |
tasksource/brainteasers |
WP |
|
brainteasers |
MultipleChoice |
| 624 |
persuasion |
Anthropic/persuasion |
|
|
persuasiveness |
Classification |
| 625 |
AmbigNQ-clarifying-question |
erbacher/AmbigNQ-clarifying-question |
|
|
ambigNQ |
Classification |
| 626 |
SIGA-nli |
tasksource/SIGA-nli |
|
|
siga_nli |
Classification |
| 627 |
FOL-nli |
unigram/FOL-nli |
|
|
unigram_fol |
Classification |
| 628 |
goal-step-wikihow/order |
tasksource/goal-step-wikihow |
order |
|
gs_order |
MultipleChoice |
| 629 |
PARADISE |
GGLab/PARADISE |
|
|
paradise |
MultipleChoice |
| 630 |
doc-nli |
tasksource/doc-nli |
|
|
docnli |
Classification |
| 631 |
mctest-nli |
tasksource/mctest-nli |
|
|
mctest_nli |
Classification |
| 632 |
patent-phrase-similarity |
tasksource/patent-phrase-similarity |
|
|
patent_phrase_similarity |
Classification |
| 633 |
natural-language-satisfiability |
tasksource/natural-language-satisfiability |
|
|
nlsat |
Classification |
| 634 |
idioms-nli |
tasksource/idioms-nli |
|
|
idioms_nli |
Classification |
| 635 |
lifecycle-entailment |
tasksource/lifecycle-entailment |
|
|
lifeycle_entailment |
Classification |
| 636 |
HelpSteer2/helpfulness |
nvidia/HelpSteer2 |
|
helpfulness |
helpsteer_2__helpfulness |
Classification |
| 637 |
HelpSteer2/correctness |
nvidia/HelpSteer2 |
|
correctness |
helpsteer_2__correctness |
Classification |
| 638 |
HelpSteer2/coherence |
nvidia/HelpSteer2 |
|
coherence |
helpsteer_2__coherence |
Classification |
| 639 |
HelpSteer2/complexity |
nvidia/HelpSteer2 |
|
complexity |
helpsteer_2__complexity |
Classification |
| 640 |
HelpSteer2/verbosity |
nvidia/HelpSteer2 |
|
verbosity |
helpsteer_2__verbosity |
Classification |
| 641 |
HelpSteer/helpfulness |
nvidia/HelpSteer |
|
helpfulness |
helpsteer__helpfulness |
Classification |
| 642 |
HelpSteer/correctness |
nvidia/HelpSteer |
|
correctness |
helpsteer__correctness |
Classification |
| 643 |
HelpSteer/coherence |
nvidia/HelpSteer |
|
coherence |
helpsteer__coherence |
Classification |
| 644 |
HelpSteer/complexity |
nvidia/HelpSteer |
|
complexity |
helpsteer__complexity |
Classification |
| 645 |
HelpSteer/verbosity |
nvidia/HelpSteer |
|
verbosity |
helpsteer__verbosity |
Classification |
| 646 |
MSciNLI |
sadat2307/MSciNLI |
|
|
msci_nli |
Classification |
| 647 |
lex_glue/ecthr_a |
coastalcph/lex_glue |
ecthr_a |
|
lex_glue___ecthr_a |
Classification |
| 648 |
lex_glue/ecthr_b |
lex_glue |
ecthr_b |
|
lex_glue___ecthr_b |
Classification |
| 649 |
UltraFeedback-paired |
pushpdeep/UltraFeedback-paired |
|
|
ultrafeedback |
MultipleChoice |
| 650 |
AES2-essay-scoring |
tasksource/AES2-essay-scoring |
|
|
essay_scoring |
Classification |
| 651 |
argument-feedback |
tasksource/argument-feedback |
|
|
argument_feedback |
Classification |
| 652 |
english-grading/cohesion |
tasksource/english-grading |
|
cohesion |
grading__cohesion |
Classification |
| 653 |
english-grading/syntax |
tasksource/english-grading |
|
syntax |
grading__syntax |
Classification |
| 654 |
english-grading/vocabulary |
tasksource/english-grading |
|
vocabulary |
grading__vocabulary |
Classification |
| 655 |
english-grading/phraseology |
tasksource/english-grading |
|
phraseology |
grading__phraseology |
Classification |
| 656 |
english-grading/grammar |
tasksource/english-grading |
|
grammar |
grading__grammar |
Classification |
| 657 |
english-grading/conventions |
tasksource/english-grading |
|
conventions |
grading__conventions |
Classification |