{"_id": {"$oid": "6a26c67c3572c06bc1455d9c"}, "test_id": "T1023", "benchmark": "business_letters", "date": "2026-04-21", "tags": {"document-type": ["letter"], "writing": ["typed", "handwritten"], "century": [20], "language": ["de"], "layout": ["prose"], "entry-type": ["person", "location"], "task": ["information-extraction"]}, "contributors": ["eric_decker", "maximilian_hindermann", "lea_kasper", "anthea_alberto", "pema_frick", "jose_luis_losada_palenzuela", "sorin_marti", "elena_spadini"], "hidden": false, "config": {"provider": "anthropic", "model": "claude-opus-4-7", "dataclass": "Document", "temperature": 0.0, "role_description": "You are a historian with keyword knowledge and an expert in the field of 20th century Swiss history", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "            IDENTITY and PURPOSE:\n\n            You are presented with a series of images constituting a historical letter. Your task is to extract the\n            values of the following keys from the letter and return them in a JSON file where the values\n            corresponding to each key should be stored as a list, even if there is only a single value for a\n            key:\n\n            - letter_title: Title of the letter.\n            - sender_persons: Name(s) of the person(s) who wrote the letter.\n            - send_date: The exact or approximate date the letter was written.\n            - receiver_persons: Name(s) of the person(s) who received the letter.\n\n            Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims\n            and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for\n            dates. If a piece of information is not included in the letter, set the value for the corresponding key\n            to \"null\". Do not return anything except the JSON file.\n\n            EXAMPLE:\n\n            {\n                \"letter_title\": [\"Petition for Environmental Protection\"],\n                \"send_date\": [\"1993-03-12\"],\n                \"sender_persons\": [\"Lisa Simpson\"],\n                \"receiver_persons\": [\"Mayor Joe Quimby\", \"Seymour Skinner\"],\n            }\n\n            OUTPUT:", "results": {"text": "{\"metadata\": {\"send_date\": [\"1932-10-10\"], \"letter_title\": [null], \"sender_persons\": [\"Jean Frey\"], \"receiver_persons\": [\"Max Vischer\"]}}", "model": "claude-opus-4-7", "provider": "anthropic", "finish_reason": "tool_use", "usage": {"input_tokens": 5539, "output_tokens": 102, "total_tokens": 5641, "input_cost_usd": 0.027694999999999997, "output_cost_usd": 0.00255, "estimated_cost_usd": 0.030244999999999998}, "duration": 5.289914131164551, "timestamp": "2026-04-21T22:58:35.798531", "parsed": {"metadata": {"send_date": ["1932-10-10"], "letter_title": [null], "sender_persons": ["Jean Frey"], "receiver_persons": ["Max Vischer"], "document_number": "letter55"}}, "conversation_id": "7c2ce93d-b3e4-43eb-8eeb-8d22fbe21d9d", "score": {"send_date_tp": 1, "send_date_fp": 0, "send_date_fn": 0, "sender_persons_tp": 0, "sender_persons_fp": 1, "sender_persons_fn": 1, "receiver_persons_tp": 1, "receiver_persons_fp": 0, "receiver_persons_fn": 0}, "raw_response": "{\"id\":\"msg_013LKMYXiu7mXt4BgpYP6Gy5\",\"container\":null,\"content\":[{\"id\":\"toolu_01WFWgAZhEeoF4Lg6eXD12dK\",\"caller\":{\"type\":\"direct\"},\"input\":{\"metadata\":{\"send_date\":[\"1932-10-10\"],\"letter_title\":[null],\"sender_persons\":[\"Jean Frey\"],\"receiver_persons\":[\"Max Vischer\"],\"document_number\":\"letter55\"}},\"name\":\"extract_structured_data\",\"type\":\"tool_use\"}],\"model\":\"claude-opus-4-7\",\"role\":\"assistant\",\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"cache_creation\":{\"ephemeral_1h_input_tokens\":0,\"ephemeral_5m_input_tokens\":0},\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"inference_geo\":\"global\",\"input_tokens\":5539,\"output_tokens\":102,\"server_tool_use\":null,\"service_tier\":\"standard\"},\"stop_details\":null}"}, "scoring": {"f1_macro": 0.63, "f1_micro": 0.66, "cost_summary": {"total_input_tokens": 473614, "total_output_tokens": 6729, "total_tokens": 480343, "input_cost_usd": 2.368070000000001, "output_cost_usd": 0.16822499999999993, "total_cost_usd": 2.536295}}, "normalized_score": 63.0}