{"_id": {"$oid": "6a26c67c3572c06bc1455ef0"}, "test_id": "T1105", "benchmark": "business_letters", "date": "2026-06-08", "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": "x-ai", "model": "grok-4.3", "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", "rules": "{\"skip_signatures\": false, \"skip_non_signatures\": true}", "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\":[\"1928-05-10\"],\"letter_title\":[\"Betr. Abrechnung\"],\"sender_persons\":[\"R. M\u00fcller\",\"W. Altermatt\"],\"receiver_persons\":[\"null\"]}}", "model": "grok-4.3", "provider": "x-ai", "finish_reason": "stop", "usage": {"input_tokens": 3009, "output_tokens": 61, "total_tokens": 3688, "cached_tokens": 3008, "input_cost_usd": 0.00376125, "output_cost_usd": 0.0001525, "estimated_cost_usd": 0.00391375}, "duration": 9.166538953781128, "timestamp": "2026-06-08T11:40:31.920981", "parsed": {"metadata": {"send_date": ["1928-05-10"], "letter_title": ["Betr. Abrechnung"], "sender_persons": ["R. M\u00fcller", "W. Altermatt"], "receiver_persons": ["null"], "document_number": "letter34"}}, "conversation_id": "498ab211-5d35-4676-bbca-babf49a33814", "score": {"send_date_tp": 1, "send_date_fp": 0, "send_date_fn": 0, "sender_persons_tp": 0, "sender_persons_fp": 2, "sender_persons_fn": 2, "receiver_persons_tp": 0, "receiver_persons_fp": 0, "receiver_persons_fn": 0}, "raw_response": "{\"id\":\"f9dfedb1-50f9-9af2-a975-0817381df947\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"metadata\\\": {\\n    \\\"send_date\\\": [\\\"1928-05-10\\\"],\\n    \\\"letter_title\\\": [\\\"Betr. Abrechnung\\\"],\\n    \\\"sender_persons\\\": [\\\"R. M\u00fcller\\\", \\\"W. Altermatt\\\"],\\n    \\\"receiver_persons\\\": [\\\"null\\\"]\\n  }\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"parsed\":{\"metadata\":{\"send_date\":[\"1928-05-10\"],\"letter_title\":[\"Betr. Abrechnung\"],\"sender_persons\":[\"R. M\u00fcller\",\"W. Altermatt\"],\"receiver_persons\":[\"null\"]}},\"reasoning_content\":\"The task is to extract specific information from the historical letter image and return it in a JSON format. The keys are:\\n\"}}],\"created\":1780911624,\"model\":\"grok-4.3\",\"object\":\"chat.completion\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_eb3c003fc66c14ed\",\"usage\":{\"completion_tokens\":61,\"prompt_tokens\":3009,\"total_tokens\":3688,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":618,\"rejected_prediction_tokens\":0},\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":3008,\"text_tokens\":629,\"image_tokens\":2380},\"num_sources_used\":0,\"cost_in_usd_ticks\":52741000}}"}, "scoring": {"f1_macro": 0.67, "f1_micro": 0.59, "cost_summary": {"total_input_tokens": 170130, "total_output_tokens": 1781, "total_tokens": 171911, "input_cost_usd": 0.21266249999999992, "output_cost_usd": 0.0044525, "total_cost_usd": 0.21711500000000006}}, "normalized_score": 67.0}