{"_id": {"$oid": "6a26c67c3572c06bc1455ee9"}, "test_id": "T1103", "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", "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\":[\"1928-05-26\"],\"letter_title\":null,\"sender_persons\":[\"Dr. Rud. Speich\"],\"receiver_persons\":[\"Dr. Max Vischer\"]}}", "model": "grok-4.3", "provider": "x-ai", "finish_reason": "stop", "usage": {"input_tokens": 5391, "output_tokens": 56, "total_tokens": 5994, "cached_tokens": 128, "input_cost_usd": 0.00673875, "output_cost_usd": 0.00014, "estimated_cost_usd": 0.00687875}, "duration": 6.238687992095947, "timestamp": "2026-06-08T11:39:47.287312", "parsed": {"metadata": {"send_date": ["1928-05-26"], "letter_title": null, "sender_persons": ["Dr. Rud. Speich"], "receiver_persons": ["Dr. Max Vischer"], "document_number": "letter39"}}, "conversation_id": "e98b2321-4d55-49d2-92a4-7a8af4a6714e", "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\":\"58cf0c19-0103-97b9-a35b-caa4064060db\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"metadata\\\": {\\n    \\\"send_date\\\": [\\\"1928-05-26\\\"],\\n    \\\"letter_title\\\": null,\\n    \\\"sender_persons\\\": [\\\"Dr. Rud. Speich\\\"],\\n    \\\"receiver_persons\\\": [\\\"Dr. Max Vischer\\\"]\\n  }\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"parsed\":{\"metadata\":{\"send_date\":[\"1928-05-26\"],\"letter_title\":null,\"sender_persons\":[\"Dr. Rud. Speich\"],\"receiver_persons\":[\"Dr. Max Vischer\"]}},\"reasoning_content\":\"The task is to extract specific information from the letter images and return it in a JSON format with lists for each value.\\n\"}}],\"created\":1780911582,\"model\":\"grok-4.3\",\"object\":\"chat.completion\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_eb3c003fc66c14ed\",\"usage\":{\"completion_tokens\":56,\"prompt_tokens\":5391,\"total_tokens\":5994,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":547,\"rejected_prediction_tokens\":0},\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":128,\"text_tokens\":631,\"image_tokens\":4760},\"num_sources_used\":0,\"cost_in_usd_ticks\":81118500}}"}, "scoring": {"f1_macro": 0.64, "f1_micro": 0.65, "cost_summary": {"total_input_tokens": 269175, "total_output_tokens": 3027, "total_tokens": 272202, "input_cost_usd": 0.33646874999999976, "output_cost_usd": 0.0075675, "total_cost_usd": 0.34403625}}, "normalized_score": 64.0}