variables: 736549

This table contains all the variables of all the datasets we have at Our World In Data. Note that this includes only the information about the variables like name and default display settings, not the data itself.

Data license: CC-BY

This data as json

id name unit description createdAt updatedAt code coverage timespan datasetId sourceId shortUnit display columnOrder originalMetadata grapherConfigAdmin shortName catalogPath dimensions schemaVersion processingLevel processingLog titlePublic titleVariant attributionShort attribution descriptionShort descriptionFromProducer descriptionKey descriptionProcessing licenses license grapherConfigETL type sort dataChecksum metadataChecksum
736549 Average accuracy on all knowledge tests - state of the art % This benchmark assesses the average accuracy of models across all subjects based on the MMLU benchmark. The MMLU benchmark covers a wide range of 57 subjects, including STEM, humanities, social sciences, and more. It encompasses subjects of varying difficulty levels, spanning from elementary concepts to advanced professional topics. This comprehensive benchmark assesses not only world knowledge but also problem-solving abilities. 2023-07-03 14:54:56 2024-07-08 16:38:15       6103 29583 % 
{
    "name": "All knowledge tests",
    "unit": "%",
    "zeroDay": "2019-01-01",
    "shortUnit": "%",
    "yearIsDay": true,
    "numDecimalPlaces": 1
}
 0     performance_language_average_state_of_the_art grapher/artificial_intelligence/2023-06-14/papers_with_code_benchmarks_state_of_the_art/papers_with_code_benchmarks_state_of_the_art#performance_language_average_state_of_the_art   1                 
[]
         float 
[]
 af0bf91d65df364d67dd163d4e44a25e 0d9d524a5be665904706435b4fb42429

Links from other tables