Index of /helm/benchmark_output/releases/v1.1.0-canary/groups/json

	Name	Last modified	Size	Description
	Parent Directory		-
	core_scenarios_general_information.json	14-Feb-2024 14:13	811K
	targeted_evaluations_general_information.json	09-Jan-2024 17:38	644K
	targeted_evaluations_efficiency_detailed.json	09-Jan-2024 17:38	512K
	math_chain_of_thought_math_chain_of_thought.json	14-Feb-2024 14:13	280K
	reasoning_general_information.json	09-Jan-2024 17:38	269K
	question_answering_general_information.json	09-Jan-2024 17:38	246K
	core_scenarios_bias.json	09-Jan-2024 17:38	179K
	mmlu_mmlu.json	14-Feb-2024 14:13	177K
	core_scenarios_efficiency.json	14-Feb-2024 14:13	176K
	core_scenarios_accuracy.json	14-Feb-2024 14:13	174K
	knowledge_general_information.json	09-Jan-2024 17:38	161K
	legalbench_legalbench.json	14-Feb-2024 14:13	154K
	wmt_14_wmt_14.json	14-Feb-2024 14:13	139K
	calibration_calibration_detailed.json	09-Jan-2024 17:38	134K
	targeted_evaluations_bias.json	09-Jan-2024 17:38	105K
	targeted_evaluations_accuracy.json	09-Jan-2024 17:38	92K
	question_answering_bias.json	09-Jan-2024 17:38	83K
	core_scenarios_robustness.json	09-Jan-2024 17:38	68K
	core_scenarios_fairness.json	09-Jan-2024 17:38	68K
	math_chain_of_thought_math_chain_of_thought_subject:counting_and_probability,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	67K
	math_chain_of_thought_math_chain_of_thought_subject:intermediate_algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	67K
	math_chain_of_thought_math_chain_of_thought_subject:geometry,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	66K
	math_chain_of_thought_math_chain_of_thought_subject:prealgebra,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	65K
	math_chain_of_thought_math_chain_of_thought_subject:precalculus,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	65K
	math_chain_of_thought_math_chain_of_thought_subject:number_theory,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	65K
	math_chain_of_thought_math_chain_of_thought_subject:algebra,level:1,use_official_examples:False,use_chain_of_thought:True.json	14-Feb-2024 14:13	65K
	core_scenarios_summarization_metrics.json	09-Jan-2024 17:38	62K
	natural_qa_openbook_longans_natural_qa_openbook_longans_mode:openbook_longans.json	14-Feb-2024 14:13	59K
	legalbench_legalbench_subset:corporate_lobbying.json	14-Feb-2024 14:13	58K
	legalbench_legalbench_subset:function_of_decision_section.json	14-Feb-2024 14:13	58K
	legalbench_legalbench_subset:international_citizenship_questions.json	14-Feb-2024 14:13	58K
	mmlu_mmlu_subject:econometrics.json	14-Feb-2024 14:13	58K
	mmlu_mmlu_subject:us_foreign_policy.json	14-Feb-2024 14:13	58K
	mmlu_mmlu_subject:computer_security.json	14-Feb-2024 14:13	58K
	mmlu_mmlu_subject:college_chemistry.json	14-Feb-2024 14:13	58K
	mmlu_mmlu_subject:abstract_algebra.json	14-Feb-2024 14:13	58K
	wmt_14_wmt_14_source_language:hi,target_language:en.json	14-Feb-2024 14:13	57K
	natural_qa_closedbook_natural_qa_closedbook_mode:closedbook.json	14-Feb-2024 14:13	57K
	wmt_14_wmt_14_source_language:de,target_language:en.json	14-Feb-2024 14:13	57K
	wmt_14_wmt_14_source_language:ru,target_language:en.json	14-Feb-2024 14:13	57K
	wmt_14_wmt_14_source_language:fr,target_language:en.json	14-Feb-2024 14:13	57K
	wmt_14_wmt_14_source_language:cs,target_language:en.json	14-Feb-2024 14:13	57K
	openbookqa_openbookqa_.json	14-Feb-2024 14:13	57K
	legalbench_legalbench_subset:abercrombie.json	14-Feb-2024 14:13	56K
	narrative_qa_narrative_qa_.json	14-Feb-2024 14:13	55K
	legalbench_legalbench_subset:proa.json	14-Feb-2024 14:13	55K
	core_scenarios_calibration.json	09-Jan-2024 17:38	55K
	med_qa_med_qa_.json	14-Feb-2024 14:13	54K
	gsm_gsm_.json	14-Feb-2024 14:13	53K
	question_answering_robustness.json	09-Jan-2024 17:38	52K
	question_answering_fairness.json	09-Jan-2024 17:38	51K
	question_answering_accuracy.json	09-Jan-2024 17:38	50K
	reasoning_efficiency.json	09-Jan-2024 17:38	49K
	reasoning_accuracy.json	09-Jan-2024 17:38	49K
	core_scenarios_toxicity.json	09-Jan-2024 17:38	45K
	question_answering_calibration.json	09-Jan-2024 17:38	45K
	question_answering_efficiency.json	09-Jan-2024 17:38	40K
	knowledge_accuracy.json	09-Jan-2024 17:38	35K
	targeted_evaluations_robustness.json	09-Jan-2024 17:38	33K
	knowledge_robustness.json	09-Jan-2024 17:38	32K
	targeted_evaluations_fairness.json	09-Jan-2024 17:38	32K
	knowledge_fairness.json	09-Jan-2024 17:38	32K
	targeted_evaluations_calibration.json	09-Jan-2024 17:38	28K
	knowledge_calibration.json	09-Jan-2024 17:38	28K
	targeted_evaluations_toxicity.json	09-Jan-2024 17:38	28K
	knowledge_efficiency.json	09-Jan-2024 17:38	28K
	targeted_evaluations_copyright_metrics.json	09-Jan-2024 17:38	24K
	question_answering_toxicity.json	09-Jan-2024 17:38	23K
	knowledge_bias.json	09-Jan-2024 17:38	23K
	calibration_accuracy.json	09-Jan-2024 17:38	22K
	targeted_evaluations_disinformation_metrics.json	09-Jan-2024 17:38	18K
	targeted_evaluations_bbq_metrics.json	09-Jan-2024 17:38	12K
	targeted_evaluations_apps_metrics.json	09-Jan-2024 17:38	12K
	reasoning_apps_metrics.json	09-Jan-2024 17:38	12K
	knowledge_toxicity.json	09-Jan-2024 17:38	9.6K