open-llm-leaderboard-old/details_harshitv804__MetaMath-Mistral-2x7B

该数据集是在Open LLM Leaderboard上对模型harshitv804/MetaMath-Mistral-2x7B进行评估时自动创建的。它由63个配置组成，每个配置对应一个被评估的任务。数据集是从1次运行中创建的，每次运行作为每个配置中的一个特定分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。一个额外的配置results存储了运行的所有聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用提供的Python代码片段加载数据集。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 harshitv804/MetaMath-Mistral-2x7B 进行评估运行期间自动创建的。数据集包含63个配置，每个配置对应一个评估任务。数据集从1次运行中创建，每次运行的详细信息可以在每个配置中找到，使用运行的时间戳作为分割名称。"train" 分割始终指向最新的结果。此外，一个名为 "results" 的配置存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是 最新结果 的摘要：

python { "all": { "acc": 0.6218089799272568, "acc_stderr": 0.03263681999096668, "acc_norm": 0.6219459868041436, "acc_norm_stderr": 0.03330427342622862, "mc1": 0.3023255813953488, "mc1_stderr": 0.016077509266133026, "mc2": 0.4479737874141746, "mc2_stderr": 0.015466809789155087 }, "harness|arc:challenge|25": { "acc": 0.5708191126279863, "acc_stderr": 0.014464085894870653, "acc_norm": 0.60580204778157, "acc_norm_stderr": 0.014280522667467325 }, "harness|hellaswag|10": { "acc": 0.6441943835889266, "acc_stderr": 0.004777782584817784, "acc_norm": 0.8259310894244174, "acc_norm_stderr": 0.003783938150151617 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.690566037735849, "acc_stderr": 0.028450154794118637, "acc_norm": 0.690566037735849, "acc_norm_stderr": 0.028450154794118637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7083333333333334, "acc_stderr": 0.038009680605548594, "acc_norm": 0.7083333333333334, "acc_norm_stderr": 0.038009680605548594 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.04755129616062946, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.04755129616062946 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5787234042553191, "acc_stderr": 0.03227834510146267, "acc_norm": 0.5787234042553191, "acc_norm_stderr": 0.03227834510146267 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.025225450284067877, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.025225450284067877 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.042857142857142816, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.042857142857142816 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7258064516129032, "acc_stderr": 0.025378139970885196, "acc_norm": 0.7258064516129032, "acc_norm_stderr": 0.025378139970885196 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932022, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932022 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8549222797927462, "acc_stderr": 0.025416343096306433, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.025416343096306433 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6051282051282051, "acc_stderr": 0.0247843169421564, "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.0247843169421564 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.029381620726465073, "acc_norm": 0.36666666666666664, "acc_norm_stderr": 0.029381620726465073 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.634453781512605, "acc_stderr": 0.031282177063684614, "acc_norm": 0.634453781512605, "acc_norm_stderr": 0.031282177063684614 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.337