Index of /helm/benchmark_output/releases/v1.6.0-canary/groups/json

[ICO]NameLast modifiedSizeDescription

[DIR]Parent Directory  -  
[   ]wmt_14_wmt_14_source_language:ru,target_language:en.json26-Jul-2024 10:12 110K 
[   ]wmt_14_wmt_14_source_language:hi,target_language:en.json26-Jul-2024 10:12 110K 
[   ]wmt_14_wmt_14_source_language:fr,target_language:en.json26-Jul-2024 10:12 110K 
[   ]wmt_14_wmt_14_source_language:de,target_language:en.json26-Jul-2024 10:12 110K 
[   ]wmt_14_wmt_14_source_language:cs,target_language:en.json26-Jul-2024 10:12 110K 
[   ]wmt_14_wmt_14.json26-Jul-2024 10:12 278K 
[   ]openbookqa_openbookqa_.json26-Jul-2024 10:12 109K 
[   ]natural_qa_openbook_longans_natural_qa_openbook_longans_mode:openbook_longans.json26-Jul-2024 10:12 113K 
[   ]natural_qa_closedbook_natural_qa_closedbook_mode:closedbook.json26-Jul-2024 10:12 109K 
[   ]narrative_qa_narrative_qa_.json26-Jul-2024 10:12 106K 
[   ]mmlu_mmlu_subject:us_foreign_policy.json26-Jul-2024 10:12 111K 
[   ]mmlu_mmlu_subject:econometrics.json26-Jul-2024 10:12 112K 
[   ]mmlu_mmlu_subject:computer_security.json26-Jul-2024 10:12 111K 
[   ]mmlu_mmlu_subject:college_chemistry.json26-Jul-2024 10:12 111K 
[   ]mmlu_mmlu_subject:abstract_algebra.json26-Jul-2024 10:12 111K 
[   ]mmlu_mmlu.json26-Jul-2024 10:12 355K 
[   ]med_qa_med_qa_.json26-Jul-2024 10:12 103K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:precalculus,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 126K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:prealgebra,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 126K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:number_theory,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 125K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:intermediate_algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 128K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:geometry,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 126K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:counting_and_probability,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 129K 
[   ]math_chain_of_thought_math_chain_of_thought_subject:algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json26-Jul-2024 10:12 125K 
[   ]math_chain_of_thought_math_chain_of_thought.json26-Jul-2024 10:12 560K 
[   ]legalbench_legalbench_subset:proa.json26-Jul-2024 10:12 105K 
[   ]legalbench_legalbench_subset:international_citizenship_questions.json26-Jul-2024 10:12 112K 
[   ]legalbench_legalbench_subset:function_of_decision_section.json26-Jul-2024 10:12 112K 
[   ]legalbench_legalbench_subset:corporate_lobbying.json26-Jul-2024 10:12 112K 
[   ]legalbench_legalbench_subset:abercrombie.json26-Jul-2024 10:12 108K 
[   ]legalbench_legalbench.json26-Jul-2024 10:12 307K 
[   ]gsm_gsm_.json26-Jul-2024 10:12 102K 
[   ]core_scenarios_general_information.json26-Jul-2024 10:12 1.6M 
[   ]core_scenarios_efficiency.json26-Jul-2024 10:12 348K 
[   ]core_scenarios_accuracy.json26-Jul-2024 10:12 345K 

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