Latest benchmark results.

rag_benchmark/e2e_df.csv

@@ -23,7 +23,7 @@ CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annu
 CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,On what page are Basel III Revisions?,"[['49'], ['34'], ['52'], ['53']]",True,False,,,,
 CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,How many employees are at Citi?,"[['240,000']]",True,False,,,,
 CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,What was the revenue from legacy franchises,"[['8.5', 'billion'], ['8,472', 'million'], ['8.472', 'billion']]",True,False,,,,
-CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,How large is the new stress capital buffer?,[['4.0%']],True,False,,,,
+CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,How large is the new stress capital buffer?,[['4.0%']],False,False,,,,
 CitiAnnual,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/citi-2022-annual-report.pdf,What were total revenues of Citigroup?,"[['$75,338', 'million'], ['$75.338', 'billion'], ['$75.3', 'billion']]",True,False,,,,
 Kaiser,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/kp-annual-report-en-2019.pdf,How many employees does kaiser permanente have?,"[['217,000']]",True,False,,,,
 Kaiser,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/kp-annual-report-en-2019.pdf,How many lab results were viewed online?,"[['60.6', 'million'], ['60.6M']]",True,False,,,,
@@ -116,7 +116,7 @@ netflix,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/FINAL-Q4-22-Share
 netflix,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/FINAL-Q4-22-Shareholder-Letter.pdf,What was the operating margin in 2022?,"[['18.0%'], ['18%'], ['18 percent']]",False,False,,,,
 oracle,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/oracle-annual-report-2021-22.pdf,Who is the CFO?,[['Makarand Padalkar']],False,False,,,,
 oracle,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/oracle-annual-report-2021-22.pdf,What do Oracles revenues comprise of?,"[['License fees', 'Maintenance fees', 'Consulting fees'], ['license fees', 'maintenance fees', 'consulting fees']]",False,False,,,,
-oracle,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/oracle-annual-report-2021-22.pdf,What was operating profit margin in 2022?,"[['54%'], ['54 percent']]",False,False,,,,
+oracle,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/oracle-annual-report-2021-22.pdf,What was unconsolidated operating profit margin in 2022?,"[['54%'], ['54 percent']]",False,False,,,,
 ofss,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/ofss-annual-report-2022-23.pdf,What is the name of the new suite of componentized and cloud based services that provides banks with highly scalable self-service digital experience capabilities?,"[['Oracle Banking Cloud Services']]",False,False,,,,
 chevron2013_10k,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/chevron_2013_10K.pdf,What are the total revenues and other income reported by Chevron in 2013?,"[['228,848 million'], ['228,848,000,000'], ['229 billion'],['228.848 billion']]",False,False,,,,
 chevron2014_10k,https://enterprise-h2ogpt-public-data.s3.amazonaws.com/chevron_2014_10K.pdf,What are the total revenues and other income reported by Chevron in 2014?,"[['211,970 million'], ['211,970,000,000'], ['212 billion'],['211.970 billion']]",False,False,,,,