Task,Accuracy,Centered
hellaswag_zeroshot,0.340669,0.120892
jeopardy,0.007558,0.007558
bigbench_qa_wikidata,0.179962,0.179962
arc_easy,0.480640,0.307520
arc_challenge,0.248294,-0.002275
copa,0.450000,-0.100000
commonsense_qa,0.212121,0.015152
piqa,0.651251,0.302503
openbook_qa,0.312000,0.082667
lambada_openai,0.234232,0.234232
hellaswag,0.336288,0.115050
winograd,0.597070,0.194139
winogrande,0.528019,0.056038
bigbench_dyck_languages,0.067000,0.067000
agi_eval_lsat_ar,0.234783,0.043478
bigbench_cs_algorithms,0.361364,0.361364
bigbench_operators,0.123810,0.123810
bigbench_repeat_copy_logic,0.000000,0.000000
squad,0.059224,0.059224
coqa,0.099712,0.099712
boolq,0.586239,-0.088846
bigbench_language_identification,0.254900,0.180308
CORE,,0.107249