{ "results": { "copa": { "acc": 0.68, "acc_stderr": 0.04688261722621505 }, "piqa": { "acc": 0.6545157780195865, "acc_stderr": 0.011094802893617745, "acc_norm": 0.6605005440696409, "acc_norm_stderr": 0.011048455047173913 }, "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.4996053670086819, "acc_stderr": 0.014052481306049516 }, "hendrycksTest-abstract_algebra": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206824 }, "hendrycksTest-anatomy": { "acc": 0.2074074074074074, "acc_stderr": 0.03502553170678318, "acc_norm": 0.1925925925925926, "acc_norm_stderr": 0.03406542058502651 }, "hendrycksTest-astronomy": { "acc": 0.21052631578947367, "acc_stderr": 0.03317672787533157, "acc_norm": 0.27631578947368424, "acc_norm_stderr": 0.03639057569952924 }, "hendrycksTest-business_ethics": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "hendrycksTest-clinical_knowledge": { "acc": 0.20754716981132076, "acc_stderr": 0.02495991802891127, "acc_norm": 0.32452830188679244, "acc_norm_stderr": 0.028815615713432115 }, "hendrycksTest-college_biology": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "hendrycksTest-college_chemistry": { "acc": 0.23, "acc_stderr": 0.042295258468165085, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-college_computer_science": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "hendrycksTest-college_mathematics": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-college_medicine": { "acc": 0.2138728323699422, "acc_stderr": 0.031265112061730424, "acc_norm": 0.26011560693641617, "acc_norm_stderr": 0.03345036916788992 }, "hendrycksTest-college_physics": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993178, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077636 }, "hendrycksTest-computer_security": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-conceptual_physics": { "acc": 0.23829787234042554, "acc_stderr": 0.027851252973889764, "acc_norm": 0.1574468085106383, "acc_norm_stderr": 0.023809905196619695 }, "hendrycksTest-econometrics": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748142, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748142 }, "hendrycksTest-electrical_engineering": { "acc": 0.2896551724137931, "acc_stderr": 0.03780019230438015, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.03780019230438014 }, "hendrycksTest-elementary_mathematics": { "acc": 0.21428571428571427, "acc_stderr": 0.021132859182754433, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.021935878081184756 }, "hendrycksTest-formal_logic": { "acc": 0.2857142857142857, "acc_stderr": 0.04040610178208841, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "hendrycksTest-global_facts": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "hendrycksTest-high_school_biology": { "acc": 0.20967741935483872, "acc_stderr": 0.023157879349083522, "acc_norm": 0.2645161290322581, "acc_norm_stderr": 0.02509189237885928 }, "hendrycksTest-high_school_chemistry": { "acc": 0.16748768472906403, "acc_stderr": 0.026273086047535414, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03010833071801162 }, "hendrycksTest-high_school_computer_science": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "hendrycksTest-high_school_european_history": { "acc": 0.24242424242424243, "acc_stderr": 0.033464098810559534, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03453131801885414 }, "hendrycksTest-high_school_geography": { "acc": 0.20202020202020202, "acc_stderr": 0.028606204289229872, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03173071239071724 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.18652849740932642, "acc_stderr": 0.02811209121011748, "acc_norm": 0.23834196891191708, "acc_norm_stderr": 0.030748905363909895 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.2282051282051282, "acc_stderr": 0.021278393863586282, "acc_norm": 0.258974358974359, "acc_norm_stderr": 0.02221110681006166 }, "hendrycksTest-high_school_mathematics": { "acc": 0.2222222222222222, "acc_stderr": 0.025348097468097838, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.028317533496066468 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.20588235294117646, "acc_stderr": 0.026265024608275882, "acc_norm": 0.29411764705882354, "acc_norm_stderr": 0.029597329730978093 }, "hendrycksTest-high_school_physics": { "acc": 0.24503311258278146, "acc_stderr": 0.03511807571804724, "acc_norm": 0.2119205298013245, "acc_norm_stderr": 0.033367670865679766 }, "hendrycksTest-high_school_psychology": { "acc": 0.22201834862385322, "acc_stderr": 0.017818849564796634, "acc_norm": 0.23486238532110093, "acc_norm_stderr": 0.018175110510343578 }, "hendrycksTest-high_school_statistics": { "acc": 0.2222222222222222, "acc_stderr": 0.02835321286686346, "acc_norm": 0.24537037037037038, "acc_norm_stderr": 0.029346665094372937 }, "hendrycksTest-high_school_us_history": { "acc": 0.28431372549019607, "acc_stderr": 0.03166009679399812, "acc_norm": 0.27941176470588236, "acc_norm_stderr": 0.031493281045079556 }, "hendrycksTest-high_school_world_history": { "acc": 0.25738396624472576, "acc_stderr": 0.028458820991460285, "acc_norm": 0.2742616033755274, "acc_norm_stderr": 0.029041333510598035 }, "hendrycksTest-human_aging": { "acc": 0.3273542600896861, "acc_stderr": 0.031493846709941306, "acc_norm": 0.2645739910313901, "acc_norm_stderr": 0.029605103217038308 }, "hendrycksTest-human_sexuality": { "acc": 0.31297709923664124, "acc_stderr": 0.04066962905677697, "acc_norm": 0.3282442748091603, "acc_norm_stderr": 0.04118438565806298 }, "hendrycksTest-international_law": { "acc": 0.1652892561983471, "acc_stderr": 0.03390780612972776, "acc_norm": 0.4462809917355372, "acc_norm_stderr": 0.0453793517794788 }, "hendrycksTest-jurisprudence": { "acc": 0.23148148148148148, "acc_stderr": 0.04077494709252626, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.047500773411999854 }, "hendrycksTest-logical_fallacies": { "acc": 0.1901840490797546, "acc_stderr": 0.030833491146281235, "acc_norm": 0.26380368098159507, "acc_norm_stderr": 0.03462419931615623 }, "hendrycksTest-machine_learning": { "acc": 0.33035714285714285, "acc_stderr": 0.044642857142857144, "acc_norm": 0.21428571428571427, "acc_norm_stderr": 0.03894641120044792 }, "hendrycksTest-management": { "acc": 0.17475728155339806, "acc_stderr": 0.037601780060266224, "acc_norm": 0.23300970873786409, "acc_norm_stderr": 0.04185832598928315 }, "hendrycksTest-marketing": { "acc": 0.2863247863247863, "acc_stderr": 0.02961432369045665, "acc_norm": 0.3162393162393162, "acc_norm_stderr": 0.030463656747340244 }, "hendrycksTest-medical_genetics": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "hendrycksTest-miscellaneous": { "acc": 0.25925925925925924, "acc_stderr": 0.015671006009339572, "acc_norm": 0.2515964240102171, "acc_norm_stderr": 0.01551732236552963 }, "hendrycksTest-moral_disputes": { "acc": 0.2630057803468208, "acc_stderr": 0.02370309952525817, "acc_norm": 0.3092485549132948, "acc_norm_stderr": 0.02488314057007175 }, "hendrycksTest-moral_scenarios": { "acc": 0.24022346368715083, "acc_stderr": 0.014288343803925293, "acc_norm": 0.24692737430167597, "acc_norm_stderr": 0.014422292204808835 }, "hendrycksTest-nutrition": { "acc": 0.24183006535947713, "acc_stderr": 0.024518195641879334, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.027826109307283686 }, "hendrycksTest-philosophy": { "acc": 0.20257234726688103, "acc_stderr": 0.022827317491059682, "acc_norm": 0.28938906752411575, "acc_norm_stderr": 0.025755865922632935 }, "hendrycksTest-prehistory": { "acc": 0.21604938271604937, "acc_stderr": 0.022899162918445803, "acc_norm": 0.1882716049382716, "acc_norm_stderr": 0.021751866060815875 }, "hendrycksTest-professional_accounting": { "acc": 0.2375886524822695, "acc_stderr": 0.025389512552729903, "acc_norm": 0.24468085106382978, "acc_norm_stderr": 0.025645553622266726 }, "hendrycksTest-professional_law": { "acc": 0.2561929595827901, "acc_stderr": 0.011149173153110582, "acc_norm": 0.28292046936114734, "acc_norm_stderr": 0.011503891323188976 }, "hendrycksTest-professional_medicine": { "acc": 0.22058823529411764, "acc_stderr": 0.025187786660227248, "acc_norm": 0.21323529411764705, "acc_norm_stderr": 0.024880971512294275 }, "hendrycksTest-professional_psychology": { "acc": 0.24509803921568626, "acc_stderr": 0.017401816711427667, "acc_norm": 0.2679738562091503, "acc_norm_stderr": 0.017917974069594726 }, "hendrycksTest-public_relations": { "acc": 0.24545454545454545, "acc_stderr": 0.04122066502878285, "acc_norm": 0.2, "acc_norm_stderr": 0.03831305140884603 }, "hendrycksTest-security_studies": { "acc": 0.2979591836734694, "acc_stderr": 0.02927956741106567, "acc_norm": 0.2571428571428571, "acc_norm_stderr": 0.02797982353874455 }, "hendrycksTest-sociology": { "acc": 0.31840796019900497, "acc_stderr": 0.03294118479054095, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.03333333333333334 }, "hendrycksTest-us_foreign_policy": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-virology": { "acc": 0.3072289156626506, "acc_stderr": 0.03591566797824662, "acc_norm": 0.25903614457831325, "acc_norm_stderr": 0.03410646614071855 }, "hendrycksTest-world_religions": { "acc": 0.2982456140350877, "acc_stderr": 0.03508771929824565, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.036996580176568775 } }, "versions": { "copa": 0, "piqa": 0, "rte": 0, "winogrande": 0, "hendrycksTest-abstract_algebra": 0, "hendrycksTest-anatomy": 0, "hendrycksTest-astronomy": 0, "hendrycksTest-business_ethics": 0, "hendrycksTest-clinical_knowledge": 0, "hendrycksTest-college_biology": 0, "hendrycksTest-college_chemistry": 0, "hendrycksTest-college_computer_science": 0, "hendrycksTest-college_mathematics": 0, "hendrycksTest-college_medicine": 0, "hendrycksTest-college_physics": 0, "hendrycksTest-computer_security": 0, "hendrycksTest-conceptual_physics": 0, "hendrycksTest-econometrics": 0, "hendrycksTest-electrical_engineering": 0, "hendrycksTest-elementary_mathematics": 0, "hendrycksTest-formal_logic": 0, "hendrycksTest-global_facts": 0, "hendrycksTest-high_school_biology": 0, "hendrycksTest-high_school_chemistry": 0, "hendrycksTest-high_school_computer_science": 0, "hendrycksTest-high_school_european_history": 0, "hendrycksTest-high_school_geography": 0, "hendrycksTest-high_school_government_and_politics": 0, "hendrycksTest-high_school_macroeconomics": 0, "hendrycksTest-high_school_mathematics": 0, "hendrycksTest-high_school_microeconomics": 0, "hendrycksTest-high_school_physics": 0, "hendrycksTest-high_school_psychology": 0, "hendrycksTest-high_school_statistics": 0, "hendrycksTest-high_school_us_history": 0, "hendrycksTest-high_school_world_history": 0, "hendrycksTest-human_aging": 0, "hendrycksTest-human_sexuality": 0, "hendrycksTest-international_law": 0, "hendrycksTest-jurisprudence": 0, "hendrycksTest-logical_fallacies": 0, "hendrycksTest-machine_learning": 0, "hendrycksTest-management": 0, "hendrycksTest-marketing": 0, "hendrycksTest-medical_genetics": 0, "hendrycksTest-miscellaneous": 0, "hendrycksTest-moral_disputes": 0, "hendrycksTest-moral_scenarios": 0, "hendrycksTest-nutrition": 0, "hendrycksTest-philosophy": 0, "hendrycksTest-prehistory": 0, "hendrycksTest-professional_accounting": 0, "hendrycksTest-professional_law": 0, "hendrycksTest-professional_medicine": 0, "hendrycksTest-professional_psychology": 0, "hendrycksTest-public_relations": 0, "hendrycksTest-security_studies": 0, "hendrycksTest-sociology": 0, "hendrycksTest-us_foreign_policy": 0, "hendrycksTest-virology": 0, "hendrycksTest-world_religions": 0 } }