window.FD = {"meta":{"facts":2226,"prompts":11130,"controlled":1340,"chance":0.27,"from":1999,"to":2026},"models":[{"model":"GPT-5","key":"gpt-5","vendor":"OpenAI","small":false,"knows":0.76,"says":0.38,"acc_says":0.95,"acc_denies":0.61,"gap":0.18,"gap_lo":0.13,"gap_hi":0.22,"claims":0.39,"claims_declared":0.01,"acc":0.76,"acc_declared":0.75,"know_end":"2024Q3","claim_end":"2024Q3","self_report":"2024-10","vendor_cutoff":"2024-09"},{"model":"DeepSeek-V3.2","key":"DeepSeek-V3.2","vendor":"DeepSeek","small":false,"knows":0.54,"says":0.28,"acc_says":0.65,"acc_denies":0.48,"gap":0.08,"gap_lo":0.03,"gap_hi":0.15,"claims":0.37,"claims_declared":0.46,"acc":0.44,"acc_declared":0.43,"know_end":"2024Q3","claim_end":"2024Q4","self_report":"2024-07","vendor_cutoff":null},{"model":"GPT-4o","key":"gpt-4o","vendor":"OpenAI","small":false,"knows":0.5,"says":0.2,"acc_says":0.83,"acc_denies":0.34,"gap":0.39,"gap_lo":0.32,"gap_hi":0.45,"claims":0.33,"claims_declared":0.04,"acc":0.43,"acc_declared":0.44,"know_end":"2023Q1","claim_end":"2023Q2","self_report":"2023-10","vendor_cutoff":"2023-10"},{"model":"Llama-3.3-70B","key":"Llama-3.3-70B-Instruct","vendor":"Meta","small":false,"knows":0.43,"says":0.48,"acc_says":0.58,"acc_denies":0.29,"gap":0.28,"gap_lo":0.2,"gap_hi":0.34,"claims":0.63,"claims_declared":0.0,"acc":0.41,"acc_declared":0.41,"know_end":"2021Q2","claim_end":"2023Q1","self_report":"2023-12","vendor_cutoff":"2023-12"},{"model":"Qwen3.5-9B","key":"Qwen3.5-9B","vendor":"Alibaba","small":true,"knows":0.37,"says":0.69,"acc_says":0.4,"acc_denies":0.3,"gap":0.1,"gap_lo":0.03,"gap_hi":0.19,"claims":0.63,"claims_declared":0.53,"acc":0.31,"acc_declared":0.35},{"model":"Qwen3-8B","key":"Qwen3-8B","vendor":"Alibaba","small":true,"knows":0.36,"says":0.71,"acc_says":0.38,"acc_denies":0.31,"gap":0.06,"gap_lo":-0.01,"gap_hi":0.14,"claims":0.68,"claims_declared":0.45,"acc":0.38,"acc_declared":0.41}],"timeline":{"GPT-5":[{"p":"1999","x":1999.5,"n":48,"acc":0.8,"claim":0.292},{"p":"2000","x":2000.5,"n":48,"acc":0.824,"claim":0.312},{"p":"2001","x":2001.5,"n":48,"acc":0.676,"claim":0.375},{"p":"2002","x":2002.5,"n":48,"acc":0.697,"claim":0.354},{"p":"2003","x":2003.5,"n":48,"acc":0.867,"claim":0.417},{"p":"2004","x":2004.5,"n":48,"acc":0.793,"claim":0.333},{"p":"2005","x":2005.5,"n":48,"acc":1.0,"claim":0.458},{"p":"2006","x":2006.5,"n":48,"acc":0.939,"claim":0.417},{"p":"2007","x":2007.5,"n":48,"acc":0.844,"claim":0.438},{"p":"2008","x":2008.5,"n":48,"acc":0.714,"claim":0.458},{"p":"2009","x":2009.5,"n":48,"acc":0.906,"claim":0.458},{"p":"2010","x":2010.5,"n":48,"acc":0.893,"claim":0.375},{"p":"2011","x":2011.5,"n":48,"acc":0.839,"claim":0.417},{"p":"2012","x":2012.5,"n":48,"acc":0.963,"claim":0.5},{"p":"2013","x":2013.5,"n":48,"acc":0.885,"claim":0.479},{"p":"2014","x":2014.5,"n":48,"acc":0.912,"claim":0.562},{"p":"2015","x":2015.5,"n":48,"acc":0.875,"claim":0.562},{"p":"2016","x":2016.5,"n":48,"acc":0.944,"claim":0.5},{"p":"2017","x":2017.5,"n":48,"acc":0.92,"claim":0.479},{"p":"2018","x":2018.5,"n":48,"acc":0.962,"claim":0.583},{"p":"2019","x":2019.5,"n":48,"acc":0.914,"claim":0.583},{"p":"2020","x":2020.5,"n":48,"acc":0.833,"claim":0.688},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.931,"claim":0.569},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.957,"claim":0.569},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.9,"claim":0.529},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.893,"claim":0.608},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.895,"claim":0.451},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.903,"claim":0.5},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.861,"claim":0.588},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.875,"claim":0.46},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.929,"claim":0.431},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.909,"claim":0.49},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.862,"claim":0.569},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.861,"claim":0.51},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.846,"claim":0.392},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.963,"claim":0.431},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.333,"claim":0.196},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.46,"claim":0.02},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.3,"claim":0.0},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.174,"claim":0.0},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.426,"claim":0.0},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.25,"claim":0.0},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.308,"claim":0.0},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.333,"claim":0.0},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.359,"claim":0.0}],"DeepSeek-V3.2":[{"p":"1999","x":1999.5,"n":48,"acc":0.453,"claim":0.354},{"p":"2000","x":2000.5,"n":48,"acc":0.559,"claim":0.375},{"p":"2001","x":2001.5,"n":48,"acc":0.424,"claim":0.375},{"p":"2002","x":2002.5,"n":48,"acc":0.449,"claim":0.354},{"p":"2003","x":2003.5,"n":48,"acc":0.506,"claim":0.25},{"p":"2004","x":2004.5,"n":48,"acc":0.606,"claim":0.375},{"p":"2005","x":2005.5,"n":48,"acc":0.604,"claim":0.292},{"p":"2006","x":2006.5,"n":48,"acc":0.621,"claim":0.375},{"p":"2007","x":2007.5,"n":48,"acc":0.552,"claim":0.396},{"p":"2008","x":2008.5,"n":48,"acc":0.423,"claim":0.375},{"p":"2009","x":2009.5,"n":48,"acc":0.625,"claim":0.417},{"p":"2010","x":2010.5,"n":48,"acc":0.714,"claim":0.375},{"p":"2011","x":2011.5,"n":48,"acc":0.645,"claim":0.333},{"p":"2012","x":2012.5,"n":48,"acc":0.815,"claim":0.312},{"p":"2013","x":2013.5,"n":48,"acc":0.808,"claim":0.333},{"p":"2014","x":2014.5,"n":48,"acc":0.735,"claim":0.333},{"p":"2015","x":2015.5,"n":48,"acc":0.534,"claim":0.333},{"p":"2016","x":2016.5,"n":48,"acc":0.659,"claim":0.354},{"p":"2017","x":2017.5,"n":48,"acc":0.6,"claim":0.417},{"p":"2018","x":2018.5,"n":48,"acc":0.577,"claim":0.458},{"p":"2019","x":2019.5,"n":48,"acc":0.581,"claim":0.312},{"p":"2020","x":2020.5,"n":48,"acc":0.612,"claim":0.396},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.655,"claim":0.255},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.652,"claim":0.235},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.5,"claim":0.28},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.679,"claim":0.333},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.513,"claim":0.28},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.532,"claim":0.38},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.473,"claim":0.294},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.516,"claim":0.333},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.375,"claim":0.412},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.462,"claim":0.32},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.672,"claim":0.412},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.556,"claim":0.255},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.538,"claim":0.353},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.704,"claim":0.38},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.348,"claim":0.255},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.306,"claim":0.137},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.379,"claim":0.059},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.348,"claim":0.039},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.312,"claim":0.0},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.45,"claim":0.021},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.269,"claim":0.0},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.414,"claim":0.0},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.367,"claim":0.0}],"GPT-4o":[{"p":"1999","x":1999.5,"n":48,"acc":0.533,"claim":0.25},{"p":"2000","x":2000.5,"n":48,"acc":0.314,"claim":0.292},{"p":"2001","x":2001.5,"n":48,"acc":0.353,"claim":0.25},{"p":"2002","x":2002.5,"n":48,"acc":0.479,"claim":0.25},{"p":"2003","x":2003.5,"n":48,"acc":0.467,"claim":0.292},{"p":"2004","x":2004.5,"n":48,"acc":0.596,"claim":0.25},{"p":"2005","x":2005.5,"n":48,"acc":0.333,"claim":0.292},{"p":"2006","x":2006.5,"n":48,"acc":0.682,"claim":0.292},{"p":"2007","x":2007.5,"n":48,"acc":0.333,"claim":0.292},{"p":"2008","x":2008.5,"n":48,"acc":0.412,"claim":0.271},{"p":"2009","x":2009.5,"n":48,"acc":0.531,"claim":0.292},{"p":"2010","x":2010.5,"n":48,"acc":0.714,"claim":0.292},{"p":"2011","x":2011.5,"n":48,"acc":0.548,"claim":0.25},{"p":"2012","x":2012.5,"n":48,"acc":0.519,"claim":0.271},{"p":"2013","x":2013.5,"n":48,"acc":0.538,"claim":0.292},{"p":"2014","x":2014.5,"n":48,"acc":0.588,"claim":0.312},{"p":"2015","x":2015.5,"n":48,"acc":0.75,"claim":0.292},{"p":"2016","x":2016.5,"n":48,"acc":0.583,"claim":0.375},{"p":"2017","x":2017.5,"n":48,"acc":0.64,"claim":0.312},{"p":"2018","x":2018.5,"n":48,"acc":0.635,"claim":0.354},{"p":"2019","x":2019.5,"n":48,"acc":0.753,"claim":0.312},{"p":"2020","x":2020.5,"n":48,"acc":0.615,"claim":0.396},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.724,"claim":0.275},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.696,"claim":0.235},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.5,"claim":0.235},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.5,"claim":0.275},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.421,"claim":0.235},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.371,"claim":0.235},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.446,"claim":0.176},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.578,"claim":0.255},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.446,"claim":0.275},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.371,"claim":0.137},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.388,"claim":0.157},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.314,"claim":0.0},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.455,"claim":0.0},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.368,"claim":0.0},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.271,"claim":0.0},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.325,"claim":0.0},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.316,"claim":0.0},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.179,"claim":0.0},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.462,"claim":0.0},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.267,"claim":0.0},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.538,"claim":0.0},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.375,"claim":0.0},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.188,"claim":0.0}],"Llama-3.3-70B":[{"p":"1999","x":1999.5,"n":48,"acc":0.427,"claim":0.708},{"p":"2000","x":2000.5,"n":48,"acc":0.559,"claim":0.708},{"p":"2001","x":2001.5,"n":48,"acc":0.294,"claim":0.688},{"p":"2002","x":2002.5,"n":48,"acc":0.377,"claim":0.646},{"p":"2003","x":2003.5,"n":48,"acc":0.5,"claim":0.667},{"p":"2004","x":2004.5,"n":48,"acc":0.458,"claim":0.667},{"p":"2005","x":2005.5,"n":48,"acc":0.417,"claim":0.729},{"p":"2006","x":2006.5,"n":48,"acc":0.568,"claim":0.75},{"p":"2007","x":2007.5,"n":48,"acc":0.323,"claim":0.708},{"p":"2008","x":2008.5,"n":48,"acc":0.441,"claim":0.729},{"p":"2009","x":2009.5,"n":48,"acc":0.656,"claim":0.729},{"p":"2010","x":2010.5,"n":48,"acc":0.607,"claim":0.708},{"p":"2011","x":2011.5,"n":48,"acc":0.613,"claim":0.708},{"p":"2012","x":2012.5,"n":48,"acc":0.667,"claim":0.75},{"p":"2013","x":2013.5,"n":48,"acc":0.615,"claim":0.688},{"p":"2014","x":2014.5,"n":48,"acc":0.588,"claim":0.833},{"p":"2015","x":2015.5,"n":48,"acc":0.625,"claim":0.792},{"p":"2016","x":2016.5,"n":48,"acc":0.652,"claim":0.75},{"p":"2017","x":2017.5,"n":48,"acc":0.507,"claim":0.75},{"p":"2018","x":2018.5,"n":48,"acc":0.654,"claim":0.812},{"p":"2019","x":2019.5,"n":48,"acc":0.624,"claim":0.792},{"p":"2020","x":2020.5,"n":48,"acc":0.533,"claim":0.792},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.517,"claim":0.745},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.478,"claim":0.745},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.25,"claim":0.686},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.393,"claim":0.725},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.368,"claim":0.667},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.274,"claim":0.686},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.311,"claim":0.647},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.422,"claim":0.588},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.304,"claim":0.235},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.379,"claim":0.078},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.414,"claim":0.039},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.361,"claim":0.0},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.269,"claim":0.0},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.269,"claim":0.0},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.188,"claim":0.0},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.226,"claim":0.0},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.214,"claim":0.0},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.348,"claim":0.0},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.384,"claim":0.0},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.097,"claim":0.0},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.231,"claim":0.0},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.185,"claim":0.0},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.311,"claim":0.0}],"Qwen3.5-9B":[{"p":"1999","x":1999.5,"n":48,"acc":0.387,"claim":0.771},{"p":"2000","x":2000.5,"n":48,"acc":0.235,"claim":0.896},{"p":"2001","x":2001.5,"n":48,"acc":0.241,"claim":0.854},{"p":"2002","x":2002.5,"n":48,"acc":0.234,"claim":0.708},{"p":"2003","x":2003.5,"n":48,"acc":0.273,"claim":0.812},{"p":"2004","x":2004.5,"n":48,"acc":0.409,"claim":0.792},{"p":"2005","x":2005.5,"n":48,"acc":0.354,"claim":0.833},{"p":"2006","x":2006.5,"n":48,"acc":0.394,"claim":0.792},{"p":"2007","x":2007.5,"n":48,"acc":0.083,"claim":0.833},{"p":"2008","x":2008.5,"n":48,"acc":0.443,"claim":0.896},{"p":"2009","x":2009.5,"n":48,"acc":0.5,"claim":0.875},{"p":"2010","x":2010.5,"n":48,"acc":0.536,"claim":0.75},{"p":"2011","x":2011.5,"n":48,"acc":0.516,"claim":0.854},{"p":"2012","x":2012.5,"n":48,"acc":0.519,"claim":0.917},{"p":"2013","x":2013.5,"n":48,"acc":0.462,"claim":0.833},{"p":"2014","x":2014.5,"n":48,"acc":0.529,"claim":0.854},{"p":"2015","x":2015.5,"n":48,"acc":0.515,"claim":0.917},{"p":"2016","x":2016.5,"n":48,"acc":0.523,"claim":0.854},{"p":"2017","x":2017.5,"n":48,"acc":0.493,"claim":0.896},{"p":"2018","x":2018.5,"n":48,"acc":0.375,"claim":0.917},{"p":"2019","x":2019.5,"n":48,"acc":0.333,"claim":0.812},{"p":"2020","x":2020.5,"n":48,"acc":0.445,"claim":0.896},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.483,"claim":0.941},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.304,"claim":0.882},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.25,"claim":0.882},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.357,"claim":0.922},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.27,"claim":0.922},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.339,"claim":0.902},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.176,"claim":0.902},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.453,"claim":0.882},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.304,"claim":0.843},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.348,"claim":0.765},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.224,"claim":0.784},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.306,"claim":0.647},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.462,"claim":0.706},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.37,"claim":0.686},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.379,"claim":0.569},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.339,"claim":0.373},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.367,"claim":0.059},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.348,"claim":0.0},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.312,"claim":0.02},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.339,"claim":0.0},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.231,"claim":0.02},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.379,"claim":0.0},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.379,"claim":0.0}],"Qwen3-8B":[{"p":"1999","x":1999.5,"n":48,"acc":0.293,"claim":0.833},{"p":"2000","x":2000.5,"n":48,"acc":0.48,"claim":0.812},{"p":"2001","x":2001.5,"n":48,"acc":0.253,"claim":0.896},{"p":"2002","x":2002.5,"n":48,"acc":0.383,"claim":0.792},{"p":"2003","x":2003.5,"n":48,"acc":0.221,"claim":0.854},{"p":"2004","x":2004.5,"n":48,"acc":0.309,"claim":0.771},{"p":"2005","x":2005.5,"n":48,"acc":0.552,"claim":0.833},{"p":"2006","x":2006.5,"n":48,"acc":0.326,"claim":0.896},{"p":"2007","x":2007.5,"n":48,"acc":0.229,"claim":0.812},{"p":"2008","x":2008.5,"n":48,"acc":0.309,"claim":0.896},{"p":"2009","x":2009.5,"n":48,"acc":0.25,"claim":0.812},{"p":"2010","x":2010.5,"n":48,"acc":0.357,"claim":0.854},{"p":"2011","x":2011.5,"n":48,"acc":0.516,"claim":0.75},{"p":"2012","x":2012.5,"n":48,"acc":0.63,"claim":0.812},{"p":"2013","x":2013.5,"n":48,"acc":0.731,"claim":0.833},{"p":"2014","x":2014.5,"n":48,"acc":0.529,"claim":0.854},{"p":"2015","x":2015.5,"n":48,"acc":0.542,"claim":0.875},{"p":"2016","x":2016.5,"n":48,"acc":0.472,"claim":0.792},{"p":"2017","x":2017.5,"n":48,"acc":0.147,"claim":0.75},{"p":"2018","x":2018.5,"n":48,"acc":0.452,"claim":0.896},{"p":"2019","x":2019.5,"n":48,"acc":0.419,"claim":0.75},{"p":"2020","x":2020.5,"n":48,"acc":0.494,"claim":0.958},{"p":"2021Q1","x":2021.125,"n":51,"acc":0.345,"claim":0.882},{"p":"2021Q2","x":2021.375,"n":51,"acc":0.391,"claim":0.882},{"p":"2021Q3","x":2021.625,"n":51,"acc":0.4,"claim":0.863},{"p":"2021Q4","x":2021.875,"n":51,"acc":0.464,"claim":0.941},{"p":"2022Q1","x":2022.125,"n":51,"acc":0.25,"claim":0.902},{"p":"2022Q2","x":2022.375,"n":51,"acc":0.242,"claim":0.863},{"p":"2022Q3","x":2022.625,"n":51,"acc":0.338,"claim":0.784},{"p":"2022Q4","x":2022.875,"n":51,"acc":0.391,"claim":0.843},{"p":"2023Q1","x":2023.125,"n":51,"acc":0.268,"claim":0.804},{"p":"2023Q2","x":2023.375,"n":51,"acc":0.371,"claim":0.784},{"p":"2023Q3","x":2023.625,"n":51,"acc":0.397,"claim":0.784},{"p":"2023Q4","x":2023.875,"n":51,"acc":0.361,"claim":0.667},{"p":"2024Q1","x":2024.125,"n":51,"acc":0.346,"claim":0.608},{"p":"2024Q2","x":2024.375,"n":51,"acc":0.407,"claim":0.588},{"p":"2024Q3","x":2024.625,"n":51,"acc":0.348,"claim":0.412},{"p":"2024Q4","x":2024.875,"n":51,"acc":0.339,"claim":0.216},{"p":"2025Q1","x":2025.125,"n":51,"acc":0.367,"claim":0.314},{"p":"2025Q2","x":2025.375,"n":51,"acc":0.348,"claim":0.314},{"p":"2025Q3","x":2025.625,"n":51,"acc":0.304,"claim":0.216},{"p":"2025Q4","x":2025.875,"n":48,"acc":0.274,"claim":0.125},{"p":"2026Q1","x":2026.125,"n":51,"acc":0.231,"claim":0.333},{"p":"2026Q2","x":2026.375,"n":51,"acc":0.379,"claim":0.314},{"p":"2026Q3","x":2026.625,"n":51,"acc":0.379,"claim":0.235}]},"family":{"GPT-5":{"Macroeconomic":{"know":0.747,"says":0.384,"acc_deny":0.648},"Stock prices":{"know":0.59,"says":0.046,"acc_deny":0.57},"Fed decisions":{"know":0.941,"says":0.931,"acc_deny":0.682}},"DeepSeek-V3.2":{"Macroeconomic":{"know":0.478,"says":0.242,"acc_deny":0.475},"Stock prices":{"know":0.49,"says":0.024,"acc_deny":0.479},"Fed decisions":{"know":0.729,"says":0.886,"acc_deny":0.632}},"GPT-4o":{"Macroeconomic":{"know":0.367,"says":0.104,"acc_deny":0.345},"Stock prices":{"know":0.332,"says":0.0,"acc_deny":0.332},"Fed decisions":{"know":0.882,"says":0.892,"acc_deny":0.8}},"Llama-3.3-70B":{"Macroeconomic":{"know":0.322,"says":0.528,"acc_deny":0.29},"Stock prices":{"know":0.272,"says":0.111,"acc_deny":0.272},"Fed decisions":{"know":0.819,"says":0.889,"acc_deny":0.27}}},"pit":[{"model":"TiMaGPT","cutoff":2014,"before":0.29,"after":0.27,"diff":0.016,"lo":-0.023,"hi":0.055},{"model":"TiMaGPT","cutoff":2016,"before":0.28,"after":0.26,"diff":0.021,"lo":-0.02,"hi":0.064},{"model":"TiMaGPT","cutoff":2018,"before":0.28,"after":0.26,"diff":0.021,"lo":-0.02,"hi":0.061},{"model":"TiMaGPT","cutoff":2020,"before":0.28,"after":0.27,"diff":0.006,"lo":-0.032,"hi":0.048},{"model":"TiMaGPT","cutoff":2022,"before":0.27,"after":0.26,"diff":0.006,"lo":-0.037,"hi":0.052},{"model":"ChronoGPT","cutoff":2014,"before":0.28,"after":0.27,"diff":0.001,"lo":-0.038,"hi":0.045},{"model":"ChronoGPT","cutoff":2016,"before":0.29,"after":0.27,"diff":0.023,"lo":-0.015,"hi":0.068},{"model":"ChronoGPT","cutoff":2018,"before":0.28,"after":0.26,"diff":0.017,"lo":-0.019,"hi":0.057},{"model":"ChronoGPT","cutoff":2020,"before":0.28,"after":0.27,"diff":0.011,"lo":-0.028,"hi":0.051},{"model":"ChronoGPT","cutoff":2022,"before":0.27,"after":0.28,"diff":-0.01,"lo":-0.053,"hi":0.042},{"model":"DatedGPT","cutoff":2014,"before":0.29,"after":0.25,"diff":0.041,"lo":-0.003,"hi":0.088}],"pool":[{"key":"us-STOCK-INTC-2021-01","period":"2021-01","family":"Stock prices","q":"What was the closing price of Intel Corporation (ticker INTC) common stock on the last trading day of January 2021, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[3,"55.51 USD"],[1,"49.95 USD"],[0,"47.17 USD"],[2,"52.73 USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,3]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,0]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-STOCK-CVX-2006-01","period":"2006-01","family":"Stock prices","q":"What was the closing price of Chevron Corporation (ticker CVX) common stock on the last trading day of January 2006, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[0,"50.47 USD"],[1,"53.44 USD"],[3,"59.38 USD"],[2,"56.41 USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,3]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,3]},"GPT-4o":{"r":[0,3],"p":[0,3]},"Llama-3.3-70B":{"r":[0,2],"p":[0,1]}}},{"key":"us-JPY_PER_USD-2024-02","period":"2024-02","family":"Macroeconomic","q":"What was the monthly average exchange rate in Japanese yen per US dollar (Federal Reserve H.10) for February 2024? Use FRED series EXJPUS and round to 2 decimal places.","true":3,"opts":[[1,"146.62 JPY per USD"],[3,"149.62 JPY per USD"],[2,"148.12 JPY per USD"],[0,"145.12 JPY per USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,2]},"GPT-4o":{"p":[0,0],"r":[0,2]},"Llama-3.3-70B":{"p":[0,0],"r":[0,2]}}},{"key":"us-STOCK-GS-2021-01","period":"2021-01","family":"Stock prices","q":"What was the closing price of The Goldman Sachs Group, Inc. (ticker GS) common stock on the last trading day of January 2021, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[1,"244.05 USD"],[0,"230.49 USD"],[3,"271.17 USD"],[2,"257.61 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"p":[1,2],"r":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[0,0]}}},{"key":"us-FOMC-2010-10","period":"2010-10","family":"Fed decisions","q":"During October 2010, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[0,2]},"GPT-4o":{"r":[1,2],"p":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-CNY_PER_USD-2026-05","period":"2026-05","family":"Macroeconomic","q":"What was the monthly average exchange rate in Chinese yuan per US dollar (Federal Reserve H.10) for May 2026? Use FRED series EXCHUS and round to 4 decimal places.","true":1,"opts":[[1,"6.7996 CNY per USD"],[0,"6.7846 CNY per USD"],[2,"6.8146 CNY per USD"],[3,"6.8296 CNY per USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[0,2],"p":[0,0]}}},{"key":"us-MORTGAGE30-2021-02","period":"2021-02","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for February 2021? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":1,"opts":[[0,"2.71%"],[1,"2.81%"],[3,"3.01%"],[2,"2.91%"]],"ans":{"GPT-5":{"p":[0,1],"r":[1,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[1,1]},"GPT-4o":{"p":[0,0],"r":[0,1]},"Llama-3.3-70B":{"p":[0,2],"r":[1,0]}}},{"key":"us-STOCK-GE-2022-12","period":"2022-12","family":"Stock prices","q":"What was the closing price of GE Aerospace (ticker GE) common stock on the last trading day of December 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[1,"79.60 USD"],[3,"87.98 USD"],[2,"83.79 USD"],[0,"75.41 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[0,0]},"GPT-4o":{"p":[0,0],"r":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[0,2]}}},{"key":"us-CNY_PER_USD-2025-11","period":"2025-11","family":"Macroeconomic","q":"What was the monthly average exchange rate in Chinese yuan per US dollar (Federal Reserve H.10) for November 2025? Use FRED series EXCHUS and round to 4 decimal places.","true":1,"opts":[[1,"7.1069 CNY per USD"],[3,"7.1369 CNY per USD"],[2,"7.1219 CNY per USD"],[0,"7.0919 CNY per USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,1]},"GPT-4o":{"p":[0,1],"r":[0,0]},"Llama-3.3-70B":{"p":[0,1],"r":[0,0]}}},{"key":"us-USD_PER_EUR-2021-02","period":"2021-02","family":"Macroeconomic","q":"What was the monthly average exchange rate in US dollars per euro (Federal Reserve H.10) for February 2021? Use FRED series EXUSEU and round to 4 decimal places.","true":2,"opts":[[2,"1.2094 USD per EUR"],[1,"1.1944 USD per EUR"],[0,"1.1794 USD per EUR"],[3,"1.2244 USD per EUR"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,2]},"GPT-4o":{"p":[0,3],"r":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[1,1]}}},{"key":"us-STOCK-EBAY-2010-12","period":"2010-12","family":"Stock prices","q":"What was the closing price of eBay Inc. (ticker EBAY) common stock on the last trading day of December 2010, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[0,"26.44 USD"],[2,"29.22 USD"],[3,"30.61 USD"],[1,"27.83 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,2]},"GPT-4o":{"r":[0,2],"p":[0,3]},"Llama-3.3-70B":{"r":[0,2],"p":[0,3]}}},{"key":"us-FOMC-2021-09","period":"2021-09","family":"Fed decisions","q":"During September 2021, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[0,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-STOCK-BA-2000-07","period":"2000-07","family":"Stock prices","q":"What was the closing price of The Boeing Company (ticker BA) common stock on the last trading day of July 2000, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[2,"48.81 USD"],[1,"46.37 USD"],[0,"43.93 USD"],[3,"51.25 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,1]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"p":[0,0],"r":[0,1]}}},{"key":"us-STOCK-TXN-2017-03","period":"2017-03","family":"Stock prices","q":"What was the closing price of Texas Instruments Incorporated (ticker TXN) common stock on the last trading day of March 2017, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[1,"76.53 USD"],[3,"84.59 USD"],[0,"72.50 USD"],[2,"80.56 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,3]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,3]},"GPT-4o":{"r":[0,1],"p":[0,3]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-STOCK-EBAY-2004-07","period":"2004-07","family":"Stock prices","q":"What was the closing price of eBay Inc. (ticker EBAY) common stock on the last trading day of July 2004, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[3,"86.17 USD"],[0,"74.41 USD"],[1,"78.33 USD"],[2,"82.25 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,3]},"GPT-4o":{"r":[0,2],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,1]}}},{"key":"us-FOMC-2025-11","period":"2025-11","family":"Fed decisions","q":"During November 2025, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"r":[0,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[0,0]}}},{"key":"us-STOCK-CVX-2025-11","period":"2025-11","family":"Stock prices","q":"What was the closing price of Chevron Corporation (ticker CVX) common stock on the last trading day of November 2025, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":0,"opts":[[3,"173.81 USD"],[2,"166.25 USD"],[0,"151.13 USD"],[1,"158.69 USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-FEDFUNDS-2025-11","period":"2025-11","family":"Macroeconomic","q":"What was the monthly average effective federal funds rate for November 2025? Use FRED series FEDFUNDS and round to 2 decimal places.","true":2,"opts":[[2,"3.88%"],[3,"3.98%"],[1,"3.78%"],[0,"3.68%"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,1]},"GPT-4o":{"r":[0,3],"p":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[0,3]}}},{"key":"us-STOCK-MSFT-2024-05","period":"2024-05","family":"Stock prices","q":"What was the closing price of Microsoft Corporation (ticker MSFT) common stock on the last trading day of May 2024, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[3,"456.65 USD"],[0,"394.37 USD"],[2,"435.89 USD"],[1,"415.13 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,1]},"GPT-4o":{"r":[0,0],"p":[0,1]},"Llama-3.3-70B":{"p":[0,3],"r":[0,0]}}},{"key":"us-GS2-2022-01","period":"2022-01","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for January 2022? Use FRED series GS2 and round to 2 decimal places.","true":1,"opts":[[1,"0.98%"],[3,"1.18%"],[0,"0.88%"],[2,"1.08%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,3]},"GPT-4o":{"r":[0,1],"p":[0,3]},"Llama-3.3-70B":{"r":[1,1],"p":[0,2]}}},{"key":"us-GS10-2023-12","period":"2023-12","family":"Macroeconomic","q":"What was the monthly average 10-year US Treasury constant maturity yield for December 2023? Use FRED series GS10 and round to 2 decimal places.","true":1,"opts":[[3,"4.22%"],[1,"4.02%"],[0,"3.92%"],[2,"4.12%"]],"ans":{"GPT-5":{"p":[0,1],"r":[1,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-STOCK-BMY-2000-05","period":"2000-05","family":"Stock prices","q":"What was the closing price of Bristol-Myers Squibb Company (ticker BMY) common stock on the last trading day of May 2000, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"57.81 USD"],[2,"55.06 USD"],[0,"49.56 USD"],[1,"52.31 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,0]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-STOCK-MRK-2023-06","period":"2023-06","family":"Stock prices","q":"What was the closing price of Merck & Co., Inc. (ticker MRK) common stock on the last trading day of June 2023, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[1,"109.62 USD"],[3,"121.16 USD"],[2,"115.39 USD"],[0,"103.85 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,1]},"GPT-4o":{"r":[0,2],"p":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,0]}}},{"key":"us-FOMC-2007-11","period":"2007-11","family":"Fed decisions","q":"During November 2007, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,0],"r":[1,1]},"GPT-4o":{"p":[0,1],"r":[1,1]},"Llama-3.3-70B":{"r":[1,1],"p":[0,2]}}},{"key":"us-STOCK-DIS-2025-05","period":"2025-05","family":"Stock prices","q":"What was the closing price of The Walt Disney Company (ticker DIS) common stock on the last trading day of May 2025, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"118.69 USD"],[2,"113.04 USD"],[0,"101.74 USD"],[1,"107.39 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,0],"p":[0,1]},"GPT-4o":{"r":[0,0],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[0,0]}}},{"key":"us-FOMC-2015-05","period":"2015-05","family":"Fed decisions","q":"During May 2015, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[1,2]},"GPT-4o":{"r":[1,2],"p":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-UNRATE-2025-12","period":"2025-12","family":"Macroeconomic","q":"What was the US unemployment rate (seasonally adjusted, BLS) for December 2025? Use FRED series UNRATE and round to one decimal place.","true":2,"opts":[[0,"4.2%"],[3,"4.5%"],[1,"4.3%"],[2,"4.4%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,0]},"DeepSeek-V3.2":{"p":[0,3],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[0,3]}}},{"key":"us-STOCK-MS-2000-02","period":"2000-02","family":"Stock prices","q":"What was the closing price of Morgan Stanley (ticker MS) common stock on the last trading day of February 2000, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"73.96 USD"],[1,"66.92 USD"],[2,"70.44 USD"],[0,"63.40 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,2]},"GPT-4o":{"r":[0,3],"p":[0,0]},"Llama-3.3-70B":{"r":[0,3],"p":[0,1]}}},{"key":"us-STOCK-WFC-2024-10","period":"2024-10","family":"Stock prices","q":"What was the closing price of Wells Fargo & Company (ticker WFC) common stock on the last trading day of October 2024, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[2,"61.67 USD"],[1,"58.42 USD"],[3,"64.92 USD"],[0,"55.17 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"p":[0,1],"r":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-STOCK-SBUX-2025-11","period":"2025-11","family":"Stock prices","q":"What was the closing price of Starbucks Corporation (ticker SBUX) common stock on the last trading day of November 2025, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"78.39 USD"],[3,"91.47 USD"],[2,"87.11 USD"],[1,"82.75 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,3],"p":[0,3]},"GPT-4o":{"p":[0,0],"r":[0,3]},"Llama-3.3-70B":{"p":[0,0],"r":[0,3]}}},{"key":"us-FOMC-2005-08","period":"2005-08","family":"Fed decisions","q":"During August 2005, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"p":[0,0],"r":[1,0]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,0]},"GPT-4o":{"r":[1,0],"p":[0,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-UNRATE-2023-11","period":"2023-11","family":"Macroeconomic","q":"What was the US unemployment rate (seasonally adjusted, BLS) for November 2023? Use FRED series UNRATE and round to one decimal place.","true":2,"opts":[[1,"3.6%"],[0,"3.5%"],[2,"3.7%"],[3,"3.8%"]],"ans":{"GPT-5":{"p":[0,3],"r":[1,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[1,1]},"GPT-4o":{"r":[0,1],"p":[0,3]},"Llama-3.3-70B":{"p":[0,1],"r":[0,2]}}},{"key":"us-FOMC-2005-11","period":"2005-11","family":"Fed decisions","q":"During November 2005, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"p":[0,0],"r":[1,0]},"DeepSeek-V3.2":{"r":[0,0],"p":[1,0]},"GPT-4o":{"r":[1,0],"p":[1,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-GS2-2002-09","period":"2002-09","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for September 2002? Use FRED series GS2 and round to 2 decimal places.","true":2,"opts":[[0,"1.80%"],[1,"1.90%"],[3,"2.10%"],[2,"2.00%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,0]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,1]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,3]}}},{"key":"us-STOCK-JNJ-2011-07","period":"2011-07","family":"Stock prices","q":"What was the closing price of Johnson & Johnson (ticker JNJ) common stock on the last trading day of July 2011, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"58.31 USD"],[2,"64.79 USD"],[3,"68.03 USD"],[1,"61.55 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,0]},"GPT-4o":{"r":[0,2],"p":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,2]}}},{"key":"us-STOCK-NKE-2012-07","period":"2012-07","family":"Stock prices","q":"What was the closing price of NIKE, Inc. (ticker NKE) common stock on the last trading day of July 2012, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[2,"88.68 USD"],[3,"93.35 USD"],[1,"84.01 USD"],[0,"79.34 USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,3]},"GPT-4o":{"r":[0,2],"p":[0,1]},"Llama-3.3-70B":{"r":[0,0],"p":[0,1]}}},{"key":"us-FOMC-2011-06","period":"2011-06","family":"Fed decisions","q":"During June 2011, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"r":[1,2],"p":[1,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-FOMC-2017-11","period":"2017-11","family":"Fed decisions","q":"During November 2017, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,0]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-MORTGAGE30-2015-10","period":"2015-10","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for October 2015? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":0,"opts":[[1,"3.90%"],[0,"3.80%"],[2,"4.00%"],[3,"4.10%"]],"ans":{"GPT-5":{"r":[0,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,3]},"GPT-4o":{"p":[0,0],"r":[0,0]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-MORTGAGE30-2021-10","period":"2021-10","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for October 2021? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":2,"opts":[[0,"2.87%"],[3,"3.17%"],[1,"2.97%"],[2,"3.07%"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[0,2]},"GPT-4o":{"r":[1,2],"p":[0,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-JPY_PER_USD-2025-07","period":"2025-07","family":"Macroeconomic","q":"What was the monthly average exchange rate in Japanese yen per US dollar (Federal Reserve H.10) for July 2025? Use FRED series EXJPUS and round to 2 decimal places.","true":3,"opts":[[2,"145.70 JPY per USD"],[0,"142.70 JPY per USD"],[1,"144.20 JPY per USD"],[3,"147.20 JPY per USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,3],"p":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,0]}}},{"key":"us-CORE_CPI_YOY-2022-08","period":"2022-08","family":"Macroeconomic","q":"What was the 12-month percent change in the US CPI for All Urban Consumers less food and energy (not seasonally adjusted) for August 2022? Use FRED series CPILFENS and round to one decimal place.","true":3,"opts":[[0,"6.0%"],[3,"6.3%"],[2,"6.2%"],[1,"6.1%"]],"ans":{"GPT-5":{"r":[1,3],"p":[0,3]},"DeepSeek-V3.2":{"r":[1,1],"p":[0,2]},"GPT-4o":{"p":[0,1],"r":[1,1]},"Llama-3.3-70B":{"p":[0,2],"r":[0,1]}}},{"key":"us-FOMC-2009-12","period":"2009-12","family":"Fed decisions","q":"During December 2009, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-FOMC-2022-06","period":"2022-06","family":"Fed decisions","q":"During June 2022, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,0]},"GPT-4o":{"p":[0,0],"r":[1,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-STOCK-ORCL-2024-11","period":"2024-11","family":"Stock prices","q":"What was the closing price of Oracle Corporation (ticker ORCL) common stock on the last trading day of November 2024, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"194.08 USD"],[0,"166.36 USD"],[2,"184.84 USD"],[1,"175.60 USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,0]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,2]},"GPT-4o":{"p":[0,3],"r":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-GS2-2019-03","period":"2019-03","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for March 2019? Use FRED series GS2 and round to 2 decimal places.","true":1,"opts":[[1,"2.41%"],[3,"2.61%"],[2,"2.51%"],[0,"2.31%"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[1,2],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-FOMC-2026-02","period":"2026-02","family":"Fed decisions","q":"During February 2026, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,2]},"GPT-4o":{"p":[0,2],"r":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-FOMC-2025-02","period":"2025-02","family":"Fed decisions","q":"During February 2025, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[0,2]},"GPT-4o":{"r":[0,2],"p":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-STOCK-MS-1999-06","period":"1999-06","family":"Stock prices","q":"What was the closing price of Morgan Stanley (ticker MS) common stock on the last trading day of June 1999, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[2,"102.62 USD"],[1,"97.49 USD"],[0,"92.36 USD"],[3,"107.75 USD"]],"ans":{"GPT-5":{"r":[0,0],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,2]},"GPT-4o":{"p":[0,2],"r":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-FOMC-2026-07","period":"2026-07","family":"Fed decisions","q":"During July 2026, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[0,0]},"GPT-4o":{"p":[0,2],"r":[0,0]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-MORTGAGE30-2001-10","period":"2001-10","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for October 2001? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":0,"opts":[[2,"6.82%"],[3,"6.92%"],[1,"6.72%"],[0,"6.62%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"p":[0,1],"r":[1,1]}}},{"key":"us-FOMC-2008-04","period":"2008-04","family":"Fed decisions","q":"During April 2008, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":1,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[1,1],"r":[1,1]},"GPT-4o":{"r":[1,1],"p":[0,1]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-GS2-2006-03","period":"2006-03","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for March 2006? Use FRED series GS2 and round to 2 decimal places.","true":3,"opts":[[0,"4.43%"],[3,"4.73%"],[2,"4.63%"],[1,"4.53%"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,1]},"GPT-4o":{"p":[0,2],"r":[0,0]},"Llama-3.3-70B":{"p":[0,2],"r":[1,1]}}},{"key":"us-FOMC-2022-08","period":"2022-08","family":"Fed decisions","q":"During August 2022, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"p":[1,0],"r":[1,0]},"GPT-4o":{"r":[1,0],"p":[0,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-FOMC-2013-07","period":"2013-07","family":"Fed decisions","q":"During July 2013, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-WTI-2023-12","period":"2023-12","family":"Macroeconomic","q":"What was the monthly average WTI crude oil spot price at Cushing, Oklahoma for December 2023? Use FRED series MCOILWTICO and round to 2 decimal places.","true":1,"opts":[[3,"77.90 USD per barrel"],[0,"68.90 USD per barrel"],[2,"74.90 USD per barrel"],[1,"71.90 USD per barrel"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,1]},"GPT-4o":{"p":[0,1],"r":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[0,2]}}},{"key":"us-STOCK-QCOM-2022-11","period":"2022-11","family":"Stock prices","q":"What was the closing price of QUALCOMM Incorporated (ticker QCOM) common stock on the last trading day of November 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[1,"126.49 USD"],[2,"132.81 USD"],[3,"139.13 USD"],[0,"120.17 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,0],"p":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-UNRATE-2003-11","period":"2003-11","family":"Macroeconomic","q":"What was the US unemployment rate (seasonally adjusted, BLS) for November 2003? Use FRED series UNRATE and round to one decimal place.","true":0,"opts":[[0,"5.8%"],[1,"5.9%"],[3,"6.1%"],[2,"6.0%"]],"ans":{"GPT-5":{"r":[1,1],"p":[0,0]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,1]},"GPT-4o":{"p":[0,1],"r":[0,0]},"Llama-3.3-70B":{"r":[1,1],"p":[0,0]}}},{"key":"us-FEDFUNDS-2023-03","period":"2023-03","family":"Macroeconomic","q":"What was the monthly average effective federal funds rate for March 2023? Use FRED series FEDFUNDS and round to 2 decimal places.","true":3,"opts":[[0,"4.35%"],[3,"4.65%"],[2,"4.55%"],[1,"4.45%"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,3]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"p":[0,3],"r":[0,2]},"Llama-3.3-70B":{"p":[0,0],"r":[1,2]}}},{"key":"us-CORE_CPI_YOY-2005-07","period":"2005-07","family":"Macroeconomic","q":"What was the 12-month percent change in the US CPI for All Urban Consumers less food and energy (not seasonally adjusted) for July 2005? Use FRED series CPILFENS and round to one decimal place.","true":2,"opts":[[1,"2.0%"],[3,"2.2%"],[0,"1.9%"],[2,"2.1%"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,3]},"GPT-4o":{"p":[0,0],"r":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[1,2]}}},{"key":"us-STOCK-QCOM-2013-01","period":"2013-01","family":"Stock prices","q":"What was the closing price of QUALCOMM Incorporated (ticker QCOM) common stock on the last trading day of January 2013, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"59.42 USD"],[2,"66.02 USD"],[3,"69.32 USD"],[1,"62.72 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,1]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"p":[0,2],"r":[1,0]}}},{"key":"us-FOMC-2016-08","period":"2016-08","family":"Fed decisions","q":"During August 2016, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-STOCK-F-2023-01","period":"2023-01","family":"Stock prices","q":"What was the closing price of Ford Motor Company (ticker F) common stock on the last trading day of January 2023, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[3,"14.87 USD"],[2,"14.19 USD"],[1,"13.51 USD"],[0,"12.83 USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,0]},"GPT-4o":{"r":[0,3],"p":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,1]}}},{"key":"us-STOCK-AMZN-2001-05","period":"2001-05","family":"Stock prices","q":"What was the closing price of Amazon.com, Inc. (ticker AMZN) common stock on the last trading day of May 2001, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[1,"15.03 USD"],[0,"14.20 USD"],[2,"15.86 USD"],[3,"16.69 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,2]},"GPT-4o":{"r":[0,2],"p":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,1]}}},{"key":"us-STOCK-QCOM-2026-03","period":"2026-03","family":"Stock prices","q":"What was the closing price of QUALCOMM Incorporated (ticker QCOM) common stock on the last trading day of March 2026, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"135.22 USD"],[0,"115.90 USD"],[2,"128.78 USD"],[1,"122.34 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,2]},"GPT-4o":{"r":[0,2],"p":[0,3]},"Llama-3.3-70B":{"r":[0,1],"p":[0,3]}}},{"key":"us-CPI_YOY-2019-08","period":"2019-08","family":"Macroeconomic","q":"What was the 12-month percent change in the US Consumer Price Index for All Urban Consumers (all items, not seasonally adjusted) for August 2019? Use FRED series CPIAUCNS and round to one decimal place.","true":0,"opts":[[1,"1.9%"],[3,"2.3%"],[2,"2.1%"],[0,"1.7%"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[0,0],"p":[0,0]},"GPT-4o":{"r":[0,0],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,1]}}},{"key":"us-MORTGAGE30-2000-04","period":"2000-04","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for April 2000? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":1,"opts":[[2,"8.25%"],[3,"8.35%"],[0,"8.05%"],[1,"8.15%"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,2]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[1,2]}}},{"key":"us-FOMC-2018-08","period":"2018-08","family":"Fed decisions","q":"During August 2018, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-FOMC-1999-06","period":"1999-06","family":"Fed decisions","q":"During June 1999, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"p":[0,2],"r":[1,0]},"GPT-4o":{"r":[1,0],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,0]}}},{"key":"us-FOMC-2000-12","period":"2000-12","family":"Fed decisions","q":"During December 2000, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[0,1]},"GPT-4o":{"p":[0,2],"r":[1,1]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-GS10-2024-07","period":"2024-07","family":"Macroeconomic","q":"What was the monthly average 10-year US Treasury constant maturity yield for July 2024? Use FRED series GS10 and round to 2 decimal places.","true":1,"opts":[[0,"4.15%"],[3,"4.45%"],[1,"4.25%"],[2,"4.35%"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[1,1],"r":[1,1]},"GPT-4o":{"p":[0,2],"r":[0,2]},"Llama-3.3-70B":{"r":[0,1],"p":[0,1]}}},{"key":"us-STOCK-BAC-2011-04","period":"2011-04","family":"Stock prices","q":"What was the closing price of Bank of America Corporation (ticker BAC) common stock on the last trading day of April 2011, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":0,"opts":[[3,"14.11 USD"],[1,"12.89 USD"],[0,"12.28 USD"],[2,"13.50 USD"]],"ans":{"GPT-5":{"r":[0,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[0,0],"p":[1,0]},"GPT-4o":{"r":[0,0],"p":[0,1]},"Llama-3.3-70B":{"r":[0,3],"p":[0,1]}}},{"key":"us-MORTGAGE30-2017-04","period":"2017-04","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for April 2017? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":1,"opts":[[3,"4.25%"],[0,"3.95%"],[1,"4.05%"],[2,"4.15%"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,1]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"p":[0,1],"r":[1,0]}}},{"key":"us-STOCK-HD-2019-01","period":"2019-01","family":"Stock prices","q":"What was the closing price of The Home Depot, Inc. (ticker HD) common stock on the last trading day of January 2019, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"192.71 USD"],[1,"174.35 USD"],[2,"183.53 USD"],[0,"165.17 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,3]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,0]}}},{"key":"us-STOCK-NVDA-2002-05","period":"2002-05","family":"Stock prices","q":"What was the closing price of NVIDIA Corporation (ticker NVDA) common stock on the last trading day of May 2002, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[2,"35.13 USD"],[0,"31.79 USD"],[1,"33.46 USD"],[3,"36.80 USD"]],"ans":{"GPT-5":{"r":[0,0],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,0]},"GPT-4o":{"r":[0,3],"p":[0,0]},"Llama-3.3-70B":{"r":[0,3],"p":[0,1]}}},{"key":"us-STOCK-NVDA-2006-03","period":"2006-03","family":"Stock prices","q":"What was the closing price of NVIDIA Corporation (ticker NVDA) common stock on the last trading day of March 2006, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[3,"57.26 USD"],[0,"48.68 USD"],[2,"54.40 USD"],[1,"51.54 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,0]},"GPT-4o":{"r":[0,0],"p":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,2]}}},{"key":"us-WTI-2018-06","period":"2018-06","family":"Macroeconomic","q":"What was the monthly average WTI crude oil spot price at Cushing, Oklahoma for June 2018? Use FRED series MCOILWTICO and round to 2 decimal places.","true":2,"opts":[[1,"64.87 USD per barrel"],[0,"61.87 USD per barrel"],[2,"67.87 USD per barrel"],[3,"70.87 USD per barrel"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"r":[0,3],"p":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[1,3]}}},{"key":"us-STOCK-TGT-2007-12","period":"2007-12","family":"Stock prices","q":"What was the closing price of Target Corporation (ticker TGT) common stock on the last trading day of December 2007, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[2,"52.50 USD"],[3,"55.00 USD"],[1,"50.00 USD"],[0,"47.50 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,2]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[0,1],"p":[0,0]}}},{"key":"us-FOMC-2006-01","period":"2006-01","family":"Fed decisions","q":"During January 2006, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"p":[0,0],"r":[1,0]},"DeepSeek-V3.2":{"p":[1,1],"r":[1,0]},"GPT-4o":{"r":[1,0],"p":[1,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-JPY_PER_USD-2024-11","period":"2024-11","family":"Macroeconomic","q":"What was the monthly average exchange rate in Japanese yen per US dollar (Federal Reserve H.10) for November 2024? Use FRED series EXJPUS and round to 2 decimal places.","true":2,"opts":[[0,"150.71 JPY per USD"],[2,"153.71 JPY per USD"],[3,"155.21 JPY per USD"],[1,"152.21 JPY per USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,0]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,3]},"GPT-4o":{"p":[0,1],"r":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,1]}}},{"key":"us-FOMC-2020-04","period":"2020-04","family":"Fed decisions","q":"During April 2020, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,1],"r":[1,1]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"r":[1,1],"p":[0,2]}}},{"key":"us-MORTGAGE30-2020-04","period":"2020-04","family":"Macroeconomic","q":"What was the monthly average 30-year fixed US mortgage rate (Freddie Mac PMMS) for April 2020? Use FRED series MORTGAGE30US and round to 2 decimal places.","true":1,"opts":[[0,"3.21%"],[1,"3.31%"],[3,"3.51%"],[2,"3.41%"]],"ans":{"GPT-5":{"p":[0,1],"r":[1,1]},"DeepSeek-V3.2":{"p":[0,3],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[1,1],"p":[0,0]}}},{"key":"us-STOCK-COST-2014-02","period":"2014-02","family":"Stock prices","q":"What was the closing price of Costco Wholesale Corporation (ticker COST) common stock on the last trading day of February 2014, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[0,"110.96 USD"],[1,"116.80 USD"],[3,"128.48 USD"],[2,"122.64 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,0],"p":[1,0]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[0,2]}}},{"key":"us-STOCK-DIS-2004-06","period":"2004-06","family":"Stock prices","q":"What was the closing price of The Walt Disney Company (ticker DIS) common stock on the last trading day of June 2004, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"22.95 USD"],[3,"26.76 USD"],[1,"24.22 USD"],[2,"25.49 USD"]],"ans":{"GPT-5":{"p":[0,0],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,0]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,2]}}},{"key":"us-STOCK-UNH-2008-10","period":"2008-10","family":"Stock prices","q":"What was the closing price of UnitedHealth Group Incorporated (ticker UNH) common stock on the last trading day of October 2008, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[2,"24.92 USD"],[0,"22.54 USD"],[1,"23.73 USD"],[3,"26.11 USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,1]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,0]}}},{"key":"us-CPI_YOY-2007-02","period":"2007-02","family":"Macroeconomic","q":"What was the 12-month percent change in the US Consumer Price Index for All Urban Consumers (all items, not seasonally adjusted) for February 2007? Use FRED series CPIAUCNS and round to one decimal place.","true":3,"opts":[[0,"1.8%"],[2,"2.2%"],[3,"2.4%"],[1,"2.0%"]],"ans":{"GPT-5":{"p":[0,3],"r":[1,3]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,2]},"GPT-4o":{"p":[0,1],"r":[0,0]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-FOMC-2008-01","period":"2008-01","family":"Fed decisions","q":"During January 2008, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":1,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,1]},"GPT-4o":{"p":[0,1],"r":[1,1]},"Llama-3.3-70B":{"p":[0,1],"r":[1,1]}}},{"key":"us-STOCK-MRK-2022-02","period":"2022-02","family":"Stock prices","q":"What was the closing price of Merck & Co., Inc. (ticker MRK) common stock on the last trading day of February 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[3,"84.24 USD"],[2,"80.41 USD"],[1,"76.58 USD"],[0,"72.75 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,3],"p":[0,0]},"GPT-4o":{"r":[0,0],"p":[0,3]},"Llama-3.3-70B":{"p":[0,3],"r":[0,0]}}},{"key":"us-STOCK-TGT-2025-04","period":"2025-04","family":"Stock prices","q":"What was the closing price of Target Corporation (ticker TGT) common stock on the last trading day of April 2025, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":0,"opts":[[0,"96.70 USD"],[2,"106.38 USD"],[1,"101.54 USD"],[3,"111.22 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"p":[0,0],"r":[0,2]},"Llama-3.3-70B":{"p":[0,3],"r":[0,1]}}},{"key":"us-WTI-2022-06","period":"2022-06","family":"Macroeconomic","q":"What was the monthly average WTI crude oil spot price at Cushing, Oklahoma for June 2022? Use FRED series MCOILWTICO and round to 2 decimal places.","true":3,"opts":[[2,"111.84 USD per barrel"],[0,"105.84 USD per barrel"],[3,"114.84 USD per barrel"],[1,"108.84 USD per barrel"]],"ans":{"GPT-5":{"r":[1,3],"p":[0,3]},"DeepSeek-V3.2":{"p":[1,3],"r":[1,2]},"GPT-4o":{"p":[0,2],"r":[0,3]},"Llama-3.3-70B":{"p":[0,3],"r":[1,3]}}},{"key":"us-STOCK-MRK-2026-05","period":"2026-05","family":"Stock prices","q":"What was the closing price of Merck & Co., Inc. (ticker MRK) common stock on the last trading day of May 2026, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[1,"106.84 USD"],[0,"100.90 USD"],[2,"112.78 USD"],[3,"118.72 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,2]},"GPT-4o":{"p":[0,2],"r":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[0,2]}}},{"key":"us-FOMC-2016-02","period":"2016-02","family":"Fed decisions","q":"During February 2016, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-FOMC-2004-08","period":"2004-08","family":"Fed decisions","q":"During August 2004, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,0],"r":[1,0]},"DeepSeek-V3.2":{"r":[1,0],"p":[0,2]},"GPT-4o":{"r":[1,0],"p":[1,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-WTI-2013-12","period":"2013-12","family":"Macroeconomic","q":"What was the monthly average WTI crude oil spot price at Cushing, Oklahoma for December 2013? Use FRED series MCOILWTICO and round to 2 decimal places.","true":2,"opts":[[3,"100.63 USD per barrel"],[2,"97.63 USD per barrel"],[0,"91.63 USD per barrel"],[1,"94.63 USD per barrel"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[1,1],"p":[0,3]}}},{"key":"us-STOCK-MSFT-2022-07","period":"2022-07","family":"Stock prices","q":"What was the closing price of Microsoft Corporation (ticker MSFT) common stock on the last trading day of July 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[0,"238.62 USD"],[1,"252.66 USD"],[2,"266.70 USD"],[3,"280.74 USD"]],"ans":{"GPT-5":{"r":[1,3],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,3],"p":[0,2]},"GPT-4o":{"r":[0,3],"p":[0,3]},"Llama-3.3-70B":{"p":[0,0],"r":[1,1]}}},{"key":"us-FOMC-2007-01","period":"2007-01","family":"Fed decisions","q":"During January 2007, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,1],"r":[1,1]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-GS2-2001-03","period":"2001-03","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for March 2001? Use FRED series GS2 and round to 2 decimal places.","true":0,"opts":[[1,"4.44%"],[0,"4.34%"],[3,"4.64%"],[2,"4.54%"]],"ans":{"GPT-5":{"p":[0,0],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,1]},"GPT-4o":{"p":[0,1],"r":[0,3]},"Llama-3.3-70B":{"r":[1,2],"p":[0,1]}}},{"key":"us-FOMC-2004-07","period":"2004-07","family":"Fed decisions","q":"During July 2004, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[1,0],"p":[0,2]},"GPT-4o":{"r":[1,0],"p":[1,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,2]}}},{"key":"us-STOCK-CVX-2002-04","period":"2002-04","family":"Stock prices","q":"What was the closing price of Chevron Corporation (ticker CVX) common stock on the last trading day of April 2002, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":0,"opts":[[3,"99.73 USD"],[1,"91.05 USD"],[0,"86.71 USD"],[2,"95.39 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,2]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-FOMC-2001-07","period":"2001-07","family":"Fed decisions","q":"During July 2001, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[1,1]},"GPT-4o":{"r":[1,1],"p":[0,1]},"Llama-3.3-70B":{"p":[0,1],"r":[1,1]}}},{"key":"us-FOMC-2013-04","period":"2013-04","family":"Fed decisions","q":"During April 2013, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"p":[1,2],"r":[1,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-GS2-2023-04","period":"2023-04","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for April 2023? Use FRED series GS2 and round to 2 decimal places.","true":0,"opts":[[3,"4.32%"],[1,"4.12%"],[0,"4.02%"],[2,"4.22%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,3]},"Llama-3.3-70B":{"p":[0,2],"r":[0,2]}}},{"key":"us-FOMC-2004-04","period":"2004-04","family":"Fed decisions","q":"During April 2004, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[0,2]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-STOCK-PEP-2009-05","period":"2009-05","family":"Stock prices","q":"What was the closing price of PepsiCo, Inc. (ticker PEP) common stock on the last trading day of May 2009, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[0,"49.45 USD"],[2,"54.65 USD"],[1,"52.05 USD"],[3,"57.25 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"r":[0,3],"p":[0,0]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-FOMC-2019-09","period":"2019-09","family":"Fed decisions","q":"During September 2019, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":1,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,2]},"GPT-4o":{"p":[0,1],"r":[1,1]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-JPY_PER_USD-2025-10","period":"2025-10","family":"Macroeconomic","q":"What was the monthly average exchange rate in Japanese yen per US dollar (Federal Reserve H.10) for October 2025? Use FRED series EXJPUS and round to 2 decimal places.","true":3,"opts":[[3,"151.35 JPY per USD"],[1,"148.35 JPY per USD"],[2,"149.85 JPY per USD"],[0,"146.85 JPY per USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"p":[0,0],"r":[0,0]},"Llama-3.3-70B":{"p":[0,1],"r":[0,0]}}},{"key":"us-FOMC-2003-07","period":"2003-07","family":"Fed decisions","q":"During July 2003, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[0,0]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"r":[1,1],"p":[0,2]}}},{"key":"us-FOMC-2017-12","period":"2017-12","family":"Fed decisions","q":"During December 2017, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,0]},"GPT-4o":{"r":[1,0],"p":[0,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-STOCK-TGT-2024-10","period":"2024-10","family":"Stock prices","q":"What was the closing price of Target Corporation (ticker TGT) common stock on the last trading day of October 2024, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"135.04 USD"],[1,"142.54 USD"],[2,"150.04 USD"],[3,"157.54 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,0],"r":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,0]},"Llama-3.3-70B":{"r":[0,3],"p":[0,2]}}},{"key":"us-FOMC-2002-02","period":"2002-02","family":"Fed decisions","q":"During February 2002, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,0]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,1],"r":[1,1]}}},{"key":"us-STOCK-HD-2024-06","period":"2024-06","family":"Stock prices","q":"What was the closing price of The Home Depot, Inc. (ticker HD) common stock on the last trading day of June 2024, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[2,"361.45 USD"],[3,"378.66 USD"],[1,"344.24 USD"],[0,"327.03 USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,1]},"GPT-4o":{"r":[0,2],"p":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,0]}}},{"key":"us-FEDFUNDS-2004-08","period":"2004-08","family":"Macroeconomic","q":"What was the monthly average effective federal funds rate for August 2004? Use FRED series FEDFUNDS and round to 2 decimal places.","true":1,"opts":[[2,"1.53%"],[3,"1.63%"],[1,"1.43%"],[0,"1.33%"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,2]},"GPT-4o":{"r":[0,1],"p":[0,3]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-FOMC-2015-04","period":"2015-04","family":"Fed decisions","q":"During April 2015, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-FOMC-2019-05","period":"2019-05","family":"Fed decisions","q":"During May 2019, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-STOCK-MCD-2022-12","period":"2022-12","family":"Stock prices","q":"What was the closing price of McDonald's Corporation (ticker MCD) common stock on the last trading day of December 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[2,"263.53 USD"],[3,"276.71 USD"],[1,"250.35 USD"],[0,"237.17 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"p":[0,0],"r":[0,1]}}},{"key":"us-CORE_CPI_YOY-2006-01","period":"2006-01","family":"Macroeconomic","q":"What was the 12-month percent change in the US CPI for All Urban Consumers less food and energy (not seasonally adjusted) for January 2006? Use FRED series CPILFENS and round to one decimal place.","true":2,"opts":[[1,"2.0%"],[2,"2.1%"],[0,"1.9%"],[3,"2.2%"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,3],"r":[1,2]},"GPT-4o":{"r":[0,2],"p":[0,1]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-FOMC-2001-01","period":"2001-01","family":"Fed decisions","q":"During January 2001, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":1,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,1],"r":[1,1]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,1]},"GPT-4o":{"r":[1,1],"p":[0,1]},"Llama-3.3-70B":{"r":[1,1],"p":[0,1]}}},{"key":"us-JPY_PER_USD-2025-04","period":"2025-04","family":"Macroeconomic","q":"What was the monthly average exchange rate in Japanese yen per US dollar (Federal Reserve H.10) for April 2025? Use FRED series EXJPUS and round to 2 decimal places.","true":1,"opts":[[1,"144.13 JPY per USD"],[0,"142.63 JPY per USD"],[3,"147.13 JPY per USD"],[2,"145.63 JPY per USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,3]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,1]},"GPT-4o":{"p":[0,1],"r":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,0]}}},{"key":"us-STOCK-JPM-2026-09","period":"2026-09","family":"Stock prices","q":"What was the closing price of JPMorgan Chase & Co. (ticker JPM) common stock on the last trading day of September 2026, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[3,"347.37 USD"],[1,"314.29 USD"],[0,"297.75 USD"],[2,"330.83 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,3]},"GPT-4o":{"r":[0,3],"p":[0,3]},"Llama-3.3-70B":{"r":[0,3],"p":[0,3]}}},{"key":"us-FOMC-2016-06","period":"2016-06","family":"Fed decisions","q":"During June 2016, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[2,"left it unchanged"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,2]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-STOCK-CVX-2022-06","period":"2022-06","family":"Stock prices","q":"What was the closing price of Chevron Corporation (ticker CVX) common stock on the last trading day of June 2022, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[3,"159.26 USD"],[2,"152.02 USD"],[1,"144.78 USD"],[0,"137.54 USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[1,2]},"GPT-4o":{"r":[0,1],"p":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-GS2-2002-03","period":"2002-03","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for March 2002? Use FRED series GS2 and round to 2 decimal places.","true":1,"opts":[[3,"3.76%"],[2,"3.66%"],[1,"3.56%"],[0,"3.46%"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,1]},"DeepSeek-V3.2":{"p":[1,2],"r":[1,2]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[1,1],"p":[0,0]}}},{"key":"us-STOCK-JPM-2021-03","period":"2021-03","family":"Stock prices","q":"What was the closing price of JPMorgan Chase & Co. (ticker JPM) common stock on the last trading day of March 2021, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[3,"152.23 USD"],[0,"129.40 USD"],[1,"137.01 USD"],[2,"144.62 USD"]],"ans":{"GPT-5":{"p":[0,3],"r":[0,3]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,2]},"GPT-4o":{"r":[0,0],"p":[0,2]},"Llama-3.3-70B":{"r":[0,2],"p":[0,3]}}},{"key":"us-FOMC-2018-04","period":"2018-04","family":"Fed decisions","q":"During April 2018, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[1,0],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-STOCK-TGT-2008-08","period":"2008-08","family":"Stock prices","q":"What was the closing price of Target Corporation (ticker TGT) common stock on the last trading day of August 2008, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[1,"50.37 USD"],[2,"53.02 USD"],[3,"55.67 USD"],[0,"47.72 USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,2]},"GPT-4o":{"r":[0,2],"p":[0,0]},"Llama-3.3-70B":{"r":[0,2],"p":[0,0]}}},{"key":"us-USD_PER_EUR-2026-09","period":"2026-09","family":"Macroeconomic","q":"What was the monthly average exchange rate in US dollars per euro (Federal Reserve H.10) for September 2026? Use FRED series EXUSEU and round to 4 decimal places.","true":2,"opts":[[2,"1.1505 USD per EUR"],[3,"1.1655 USD per EUR"],[0,"1.1205 USD per EUR"],[1,"1.1355 USD per EUR"]],"ans":{"GPT-5":{"r":[0,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[0,0],"p":[0,1]},"GPT-4o":{"r":[0,2],"p":[0,1]},"Llama-3.3-70B":{"r":[0,2],"p":[0,1]}}},{"key":"us-FOMC-2020-01","period":"2020-01","family":"Fed decisions","q":"During January 2020, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"p":[0,2],"r":[1,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-FOMC-2012-06","period":"2012-06","family":"Fed decisions","q":"During June 2012, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"p":[0,2],"r":[1,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,2]}}},{"key":"us-STOCK-UNH-2000-11","period":"2000-11","family":"Stock prices","q":"What was the closing price of UnitedHealth Group Incorporated (ticker UNH) common stock on the last trading day of November 2000, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":3,"opts":[[0,"99.70 USD"],[1,"105.57 USD"],[2,"111.44 USD"],[3,"117.31 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,0]}}},{"key":"us-FOMC-2006-03","period":"2006-03","family":"Fed decisions","q":"During March 2006, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[2,"left it unchanged"],[1,"lowered it"],[0,"raised it"]],"ans":{"GPT-5":{"r":[1,0],"p":[1,0]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,0]},"GPT-4o":{"r":[1,0],"p":[1,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-CNY_PER_USD-2021-10","period":"2021-10","family":"Macroeconomic","q":"What was the monthly average exchange rate in Chinese yuan per US dollar (Federal Reserve H.10) for October 2021? Use FRED series EXCHUS and round to 4 decimal places.","true":1,"opts":[[0,"6.4022 CNY per USD"],[2,"6.4322 CNY per USD"],[1,"6.4172 CNY per USD"],[3,"6.4472 CNY per USD"]],"ans":{"GPT-5":{"p":[0,0],"r":[0,0]},"DeepSeek-V3.2":{"r":[0,0],"p":[0,1]},"GPT-4o":{"p":[0,2],"r":[0,0]},"Llama-3.3-70B":{"p":[0,3],"r":[1,1]}}},{"key":"us-FOMC-2008-07","period":"2008-07","family":"Fed decisions","q":"During July 2008, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,1],"p":[1,1]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"r":[1,1],"p":[0,2]}}},{"key":"us-CNY_PER_USD-2022-09","period":"2022-09","family":"Macroeconomic","q":"What was the monthly average exchange rate in Chinese yuan per US dollar (Federal Reserve H.10) for September 2022? Use FRED series EXCHUS and round to 4 decimal places.","true":1,"opts":[[3,"7.0495 CNY per USD"],[2,"7.0345 CNY per USD"],[1,"7.0195 CNY per USD"],[0,"7.0045 CNY per USD"]],"ans":{"GPT-5":{"p":[0,1],"r":[0,3]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,3]},"GPT-4o":{"r":[0,3],"p":[0,3]},"Llama-3.3-70B":{"r":[0,2],"p":[0,3]}}},{"key":"us-STOCK-T-2009-11","period":"2009-11","family":"Stock prices","q":"What was the closing price of AT&T Inc. (ticker T) common stock on the last trading day of November 2009, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"24.24 USD"],[3,"28.29 USD"],[2,"26.94 USD"],[1,"25.59 USD"]],"ans":{"GPT-5":{"r":[0,3],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,1]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[0,0],"p":[0,1]}}},{"key":"us-UNRATE-2026-06","period":"2026-06","family":"Macroeconomic","q":"What was the US unemployment rate (seasonally adjusted, BLS) for June 2026? Use FRED series UNRATE and round to one decimal place.","true":1,"opts":[[3,"4.4%"],[2,"4.3%"],[0,"4.1%"],[1,"4.2%"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,0]},"GPT-4o":{"r":[0,0],"p":[0,0]},"Llama-3.3-70B":{"r":[0,2],"p":[0,1]}}},{"key":"us-FOMC-2017-03","period":"2017-03","family":"Fed decisions","q":"During March 2017, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[0,"raised it"],[2,"left it unchanged"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"p":[1,0],"r":[1,0]},"GPT-4o":{"r":[1,0],"p":[0,0]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-FOMC-2004-12","period":"2004-12","family":"Fed decisions","q":"During December 2004, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[1,"lowered it"],[0,"raised it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[1,1],"p":[0,2]},"GPT-4o":{"r":[1,0],"p":[0,0]},"Llama-3.3-70B":{"p":[0,0],"r":[1,0]}}},{"key":"us-USD_PER_EUR-2024-02","period":"2024-02","family":"Macroeconomic","q":"What was the monthly average exchange rate in US dollars per euro (Federal Reserve H.10) for February 2024? Use FRED series EXUSEU and round to 4 decimal places.","true":2,"opts":[[1,"1.0643 USD per EUR"],[3,"1.0943 USD per EUR"],[0,"1.0493 USD per EUR"],[2,"1.0793 USD per EUR"]],"ans":{"GPT-5":{"r":[1,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,3]},"Llama-3.3-70B":{"p":[0,3],"r":[0,1]}}},{"key":"us-CNY_PER_USD-2021-01","period":"2021-01","family":"Macroeconomic","q":"What was the monthly average exchange rate in Chinese yuan per US dollar (Federal Reserve H.10) for January 2021? Use FRED series EXCHUS and round to 4 decimal places.","true":2,"opts":[[1,"6.4522 CNY per USD"],[2,"6.4672 CNY per USD"],[0,"6.4372 CNY per USD"],[3,"6.4822 CNY per USD"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[1,2]},"GPT-4o":{"p":[0,2],"r":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-STOCK-T-2007-07","period":"2007-07","family":"Stock prices","q":"What was the closing price of AT&T Inc. (ticker T) common stock on the last trading day of July 2007, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":1,"opts":[[2,"41.12 USD"],[3,"43.08 USD"],[0,"37.20 USD"],[1,"39.16 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,1]},"DeepSeek-V3.2":{"p":[0,1],"r":[0,2]},"GPT-4o":{"r":[0,3],"p":[0,0]},"Llama-3.3-70B":{"r":[0,1],"p":[0,1]}}},{"key":"us-FOMC-2020-12","period":"2020-12","family":"Fed decisions","q":"During December 2020, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[0,"raised it"],[1,"lowered it"],[2,"left it unchanged"]],"ans":{"GPT-5":{"r":[1,2],"p":[1,2]},"DeepSeek-V3.2":{"r":[1,2],"p":[1,2]},"GPT-4o":{"r":[1,2],"p":[0,2]},"Llama-3.3-70B":{"p":[0,2],"r":[1,2]}}},{"key":"us-GS10-2025-10","period":"2025-10","family":"Macroeconomic","q":"What was the monthly average 10-year US Treasury constant maturity yield for October 2025? Use FRED series GS10 and round to 2 decimal places.","true":1,"opts":[[3,"4.26%"],[2,"4.16%"],[0,"3.96%"],[1,"4.06%"]],"ans":{"GPT-5":{"r":[0,2],"p":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"p":[0,2],"r":[0,3]},"Llama-3.3-70B":{"r":[0,3],"p":[0,0]}}},{"key":"us-STOCK-ABT-2011-01","period":"2011-01","family":"Stock prices","q":"What was the closing price of Abbott Laboratories (ticker ABT) common stock on the last trading day of January 2011, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":0,"opts":[[0,"45.16 USD"],[1,"47.42 USD"],[3,"51.94 USD"],[2,"49.68 USD"]],"ans":{"GPT-5":{"r":[0,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,0]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"r":[0,1],"p":[0,1]}}},{"key":"us-GS2-2023-09","period":"2023-09","family":"Macroeconomic","q":"What was the monthly average 2-year US Treasury constant maturity yield for September 2023? Use FRED series GS2 and round to 2 decimal places.","true":3,"opts":[[2,"4.92%"],[1,"4.82%"],[0,"4.72%"],[3,"5.02%"]],"ans":{"GPT-5":{"r":[1,3],"p":[0,3]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,2]},"GPT-4o":{"p":[0,3],"r":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,1]}}},{"key":"us-FOMC-1999-08","period":"1999-08","family":"Fed decisions","q":"During August 1999, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":0,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"r":[1,0],"p":[0,1]},"GPT-4o":{"r":[1,0],"p":[0,2]},"Llama-3.3-70B":{"r":[1,0],"p":[0,0]}}},{"key":"us-UNRATE-2021-01","period":"2021-01","family":"Macroeconomic","q":"What was the US unemployment rate (seasonally adjusted, BLS) for January 2021? Use FRED series UNRATE and round to one decimal place.","true":2,"opts":[[0,"6.2%"],[3,"6.5%"],[2,"6.4%"],[1,"6.3%"]],"ans":{"GPT-5":{"r":[1,1],"p":[0,1]},"DeepSeek-V3.2":{"r":[1,2],"p":[0,1]},"GPT-4o":{"r":[1,1],"p":[0,2]},"Llama-3.3-70B":{"r":[1,2],"p":[0,3]}}},{"key":"us-USD_PER_EUR-2021-06","period":"2021-06","family":"Macroeconomic","q":"What was the monthly average exchange rate in US dollars per euro (Federal Reserve H.10) for June 2021? Use FRED series EXUSEU and round to 4 decimal places.","true":0,"opts":[[0,"1.2048 USD per EUR"],[3,"1.2498 USD per EUR"],[1,"1.2198 USD per EUR"],[2,"1.2348 USD per EUR"]],"ans":{"GPT-5":{"r":[1,0],"p":[0,0]},"DeepSeek-V3.2":{"p":[1,1],"r":[0,1]},"GPT-4o":{"r":[0,1],"p":[0,1]},"Llama-3.3-70B":{"r":[1,3],"p":[0,1]}}},{"key":"us-FOMC-2026-04","period":"2026-04","family":"Fed decisions","q":"During April 2026, did the Federal Reserve raise, lower, or leave unchanged its federal funds target rate (the upper bound of the target range from December 2008 on)?","true":2,"opts":[[2,"left it unchanged"],[0,"raised it"],[1,"lowered it"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"p":[0,2],"r":[0,2]},"GPT-4o":{"r":[0,2],"p":[0,2]},"Llama-3.3-70B":{"r":[0,0],"p":[0,0]}}},{"key":"us-WTI-2020-06","period":"2020-06","family":"Macroeconomic","q":"What was the monthly average WTI crude oil spot price at Cushing, Oklahoma for June 2020? Use FRED series MCOILWTICO and round to 2 decimal places.","true":1,"opts":[[1,"38.31 USD per barrel"],[2,"41.31 USD per barrel"],[3,"44.31 USD per barrel"],[0,"35.31 USD per barrel"]],"ans":{"GPT-5":{"p":[0,1],"r":[1,1]},"DeepSeek-V3.2":{"r":[0,1],"p":[0,0]},"GPT-4o":{"r":[0,1],"p":[0,0]},"Llama-3.3-70B":{"r":[1,1],"p":[0,0]}}},{"key":"us-STOCK-PFE-2021-04","period":"2021-04","family":"Stock prices","q":"What was the closing price of Pfizer Inc. (ticker PFE) common stock on the last trading day of April 2021, as quoted at the time (not adjusted for later stock splits)? Round to two decimal places.","true":2,"opts":[[0,"34.79 USD"],[3,"40.58 USD"],[1,"36.72 USD"],[2,"38.65 USD"]],"ans":{"GPT-5":{"p":[0,2],"r":[0,2]},"DeepSeek-V3.2":{"r":[0,2],"p":[0,1]},"GPT-4o":{"r":[0,2],"p":[0,3]},"Llama-3.3-70B":{"p":[0,3],"r":[0,1]}}}]};