open-llm-leaderboard-old/details_deepseek-ai__deepseek-llm-67b-base

该数据集是在评估模型deepseek-ai/deepseek-llm-67b-base时自动生成的，包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为特定的分割存储在配置中，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，results配置存储了所有运行的聚合结果，用于计算和展示在Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型deepseek-ai/deepseek-llm-67b-base在Open LLM Leaderboard上的自动创建的。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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train"分片总是指向最新的结果。

数据集结构

数据集包含以下配置：

• harness_arc_challenge_25
• harness_gsm8k_5
• harness_hellaswag_10
• harness_hendrycksTest_5

每个配置包含多个分片，包括特定时间戳的分片和最新的分片。

最新结果

以下是最新结果的摘要： python { "all": { "acc": 0.7152016597064887, "acc_stderr": 0.029610855644222223, "acc_norm": 0.7193168663591899, "acc_norm_stderr": 0.030182859586413653, "mc1": 0.3525091799265606, "mc1_stderr": 0.016724646380756544, "mc2": 0.5108013665291756, "mc2_stderr": 0.014538753767819627 }, "harness|arc:challenge|25": { "acc": 0.6262798634812287, "acc_stderr": 0.014137708601759096, "acc_norm": 0.6544368600682594, "acc_norm_stderr": 0.01389693846114568 }, "harness|hellaswag|10": { "acc": 0.6783509261103365, "acc_stderr": 0.004661544991583034, "acc_norm": 0.8710416251742681, "acc_norm_stderr": 0.003344689038650325 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6592592592592592, "acc_stderr": 0.040943762699967926, "acc_norm": 0.6592592592592592, "acc_norm_stderr": 0.040943762699967926 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8092105263157895, "acc_stderr": 0.03197565821032499, "acc_norm": 0.8092105263157895, "acc_norm_stderr": 0.03197565821032499 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7811320754716982, "acc_stderr": 0.025447863825108614, "acc_norm": 0.7811320754716982, "acc_norm_stderr": 0.025447863825108614 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8472222222222222, "acc_stderr": 0.030085743248565677, "acc_norm": 0.8472222222222222, "acc_norm_stderr": 0.030085743248565677 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7341040462427746, "acc_stderr": 0.03368762932259431, "acc_norm": 0.7341040462427746, "acc_norm_stderr": 0.03368762932259431 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7319148936170212, "acc_stderr": 0.028957342788342343, "acc_norm": 0.7319148936170212, "acc_norm_stderr": 0.028957342788342343 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5175438596491229, "acc_stderr": 0.04700708033551038, "acc_norm": 0.5175438596491229, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6827586206896552, "acc_stderr": 0.03878352372138622, "acc_norm": 0.6827586206896552, "acc_norm_stderr": 0.03878352372138622 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5026455026455027, "acc_stderr": 0.025750949678130387, "acc_norm": 0.5026455026455027, "acc_norm_stderr": 0.025750949678130387 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5317460317460317, "acc_stderr": 0.04463112720677173, "acc_norm": 0.5317460317460317, "acc_norm_stderr": 0.04463112720677173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8258064516129032, "acc_stderr": 0.021576248184514587, "acc_norm": 0.8258064516129032, "acc_norm_stderr": 0.021576248184514587 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5714285714285714, "acc_stderr": 0.034819048444388045, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.034819048444388045 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8181818181818182, "acc_stderr": 0.030117688929503582, "acc_norm": 0.8181818181818182, "acc_norm_stderr": 0.030117688929503582 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.898989898989899, "acc_stderr": 0.02146973557605533, "acc_norm": 0.898989898989899, "acc_norm_stderr": 0.02146973557605533 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084313, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084313 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7307692307692307, "acc_stderr": 0.02248938979365483, "acc_norm": 0.7307692307692307, "acc_norm_stderr": 0.02248938979365483 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37777777777777777, "acc_stderr": 0.029560707392465715, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.029560707392465715 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8235294117647058, "acc_