{"_id": {"$oid": "6ac4c7b5164e0f17c0b22e27"}, "test_id": "T0248", "benchmark": "business_letters", "date": "2025-10-17", "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": "openrouter", "model": "meta-llama/llama-4-maverick", "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": {"provider": "openrouter", "model": "meta-llama/llama-4-maverick", "duration": 3.0031960010528564, "timestamp": "2025-10-17T22:39:25.462141", "parsed": {"metadata": {"send_date": ["1926-02-16"], "letter_title": [""], "sender_persons": ["Basler Rheinschiffahrt-Aktiengesellschaft"], "receiver_persons": ["Christ"]}}, "text": "", "raw_response": {"id": "gen-1760733562-bz6wNyW0dZLaMJXqJz45", "model": "meta-llama/llama-4-maverick", "choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "{\"metadata\": {\"send_date\": [\"1926-02-16\"], \"letter_title\": [\"\"], \"sender_persons\": [\"Basler Rheinschiffahrt-Aktiengesellschaft\"], \"receiver_persons\": [\"Christ\"]}}", "role": "assistant"}}], "usage": {"prompt_tokens": 6054, "completion_tokens": 51, "total_tokens": 6105}}, "usage": {"input_tokens": 6054, "output_tokens": 51, "total_tokens": 6105, "input_cost_usd": 0.0009081, "output_cost_usd": 3.06e-05, "estimated_cost_usd": 0.0009387}, "finish_reason": "stop"}, "scoring": {"f1_macro": 0.46, "f1_micro": 0.47, "cost_summary": {"total_input_tokens": 203693, "total_output_tokens": 3574, "total_tokens": 207267, "input_cost_usd": 0.03055395, "output_cost_usd": 0.0021444, "total_cost_usd": 0.03269835, "pricing_date": "2025-10-17", "input_price_per_million": 0.15, "output_price_per_million": 0.6}}, "pricing": {"bucket_date": "2025-10-17", "age_days": 0, "input_price_per_million": 0.15, "output_price_per_million": 0.6}, "timing": {"total_response_s": 183.79, "mean_response_s": 3.22, "slowest_response_s": 10.21, "inputs_timed": 57, "inputs_stored": 57, "span_s": 188.36}, "normalized_score": 46.0}