{"task":"Odd One Out","dataset":"BIG-bench","metric_names":["Accuracy"],"rows":[{"id":120867,"task":"Odd One Out","parent_task":null,"dataset":"BIG-bench","model_name":"Chinchilla-70B (few-shot, k=5)","metrics":{"Accuracy":"70.9"},"paper_url":"https://arxiv.org/abs/2203.15556v1","paper_title":"Training Compute-Optimal Large Language Models","paper_date":"2022-03-29","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120868,"task":"Odd One Out","parent_task":null,"dataset":"BIG-bench","model_name":"Gopher-280B (few-shot, k=5)","metrics":{"Accuracy":"32.5"},"paper_url":"https://arxiv.org/abs/2112.11446v2","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_date":"2021-12-08","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}