Index of /helm/benchmark_output/releases/v1.9.0/groups/json

[ICO]NameLast modifiedSizeDescription

[DIR]Parent Directory  -  
[   ]core_scenarios_accuracy.json18-Oct-2024 12:10 385K 
[   ]core_scenarios_efficiency.json18-Oct-2024 12:10 388K 
[   ]core_scenarios_general_information.json18-Oct-2024 12:10 1.8M 
[   ]gsm_gsm_.json18-Oct-2024 12:11 113K 
[   ]legalbench_legalbench.json18-Oct-2024 12:11 344K 
[   ]legalbench_legalbench_subset:abercrombie.json18-Oct-2024 12:11 121K 
[   ]legalbench_legalbench_subset:corporate_lobbying.json18-Oct-2024 12:11 124K 
[   ]legalbench_legalbench_subset:function_of_decision_section.json18-Oct-2024 12:11 125K 
[   ]legalbench_legalbench_subset:international_citizenship_questions.json18-Oct-2024 12:11 125K 
[   ]legalbench_legalbench_subset:proa.json18-Oct-2024 12:11 118K 
[   ]math_chain_of_thought_math_chain_of_thought.json18-Oct-2024 12:11 626K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 139K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:counting_and_probability,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 143K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:geometry,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 139K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:intermediate_algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 142K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:number_theory,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 139K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:prealgebra,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 140K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:precalculus,level:1,use_official_examples:False,use_chain_of_thought:True.json18-Oct-2024 12:11 140K 
[   ]med_qa_med_qa_.json18-Oct-2024 12:11 114K 
[   ]mmlu_mmlu.json18-Oct-2024 12:11 396K 
[   ]mmlu_mmlu_subject:abstract_algebra.json18-Oct-2024 12:11 122K 
[   ]mmlu_mmlu_subject:college_chemistry.json18-Oct-2024 12:11 123K 
[   ]mmlu_mmlu_subject:computer_security.json18-Oct-2024 12:11 123K 
[   ]mmlu_mmlu_subject:econometrics.json18-Oct-2024 12:11 124K 
[   ]mmlu_mmlu_subject:us_foreign_policy.json18-Oct-2024 12:11 123K 
[   ]narrative_qa_narrative_qa_.json18-Oct-2024 12:11 118K 
[   ]natural_qa_closedbook_natural_qa_closedbook_mode:closedbook.json18-Oct-2024 12:11 121K 
[   ]natural_qa_openbook_longans_natural_qa_openbook_longans_mode:openbook_longans.json18-Oct-2024 12:11 125K 
[   ]openbookqa_openbookqa_.json18-Oct-2024 12:11 121K 
[   ]wmt_14_wmt_14.json18-Oct-2024 12:11 311K 
[   ]wmt_14_wmt_14_source_language:cs,target_language:en.json18-Oct-2024 12:11 123K 
[   ]wmt_14_wmt_14_source_language:de,target_language:en.json18-Oct-2024 12:11 123K 
[   ]wmt_14_wmt_14_source_language:fr,target_language:en.json18-Oct-2024 12:11 121K 
[   ]wmt_14_wmt_14_source_language:hi,target_language:en.json18-Oct-2024 12:11 123K 
[   ]wmt_14_wmt_14_source_language:ru,target_language:en.json18-Oct-2024 12:11 123K 

Apache/2.2.15 (CentOS) Server at nlp.stanford.edu Port 443