{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/claude-3-5-sonnet-model-card-addendum","title":"Claude 3.5 Sonnet Model Card Addendum","arxiv_id":null,"date":"2024-06-24","proceeding":"Preprint 2024 6","authors":["Anthropic"],"abstract":"This addendum to our Claude 3 Model Card describes Claude 3.5 Sonnet, a new model which outperforms\r\nour previous most capable model, Claude 3 Opus, while operating faster and at a lower cost. Claude 3.5\r\nSonnet offers improved capabilities, including better coding and visual processing. Since it is an evolution of\r\nthe Claude 3 model family, we are providing an addendum rather than a new model card. We provide updated\r\nkey evaluations and results from our safety testing.","url_abs":"https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf","url_pdf":"https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"mmr-total","task_name":"MMR total"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"Claude 3.5 Sonnet","rank_in_archive_order":1,"of":14,"metrics":{"Total Column Score":"463"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-newsqa","task":"Question Answering","dataset":"NewsQA","model":"Anthropic/claude-3-7-sonnet","rank_in_archive_order":6,"of":18,"metrics":{"EM":"74.23","F1":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Claude 3.5 Sonnet (claude-3-5-sonnet-20240620)","rank_in_archive_order":5,"of":231,"metrics":{"GPT-4 score":"74.2±0.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"Claude 3.5 Sonnet  (claude-3-5-sonnet-20240620)","rank_in_archive_order":3,"of":24,"metrics":{"GPT-4 score":"71.8±0.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}