{"_id": {"$oid": "6a8456c1ef0a19c343227d1f"}, "test_id": "T1517", "benchmark": "blacklist_cards", "date": "2026-08-15", "tags": {"document-type": ["index-card"], "writing": ["typed", "handwritten"], "century": [20], "language": ["de"], "entry-type": ["company"], "task": ["information-extraction"]}, "contributors": ["lea_kasper", "sorin_marti"], "hidden": false, "config": {"provider": "huggingface", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct:deepinfra", "dataclass": "Card", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "You are a meticulous archivist extracting data from an index card image. Analyze the provided image and extract the following information. Return the data ONLY as a valid JSON object.\n\n- \"company\": The primary company name, usually in the top-left. Exclude the location.\n- \"location\": The city or town, often following the company name.\n- \"b_id\": The identifier code, usually in the top-right, starting with \"B.\".\n- \"date\": Any stamped dates on the card in YYYY-MM-DD format. If no date is present, use an empty string.\n- \"information\": A list of text blocks from the main body of the card. Each block should be a separate string in the list. Maintain line breaks with \\\\n.\n\nHere is the required JSON format:\n{\n  \"company\": {\"transcription\": \"\"},\n  \"location\": {\"transcription\": \"\"},\n  \"b_id\": {\"transcription\": \"\"},\n  \"date\": \"\",\n  \"information\": [\n    {\"transcription\": \"\"}\n  ]\n}\n\nIf you cannot find a value for a field, leave its transcription value as an empty string. Do not add any explanatory text outside of the JSON object.", "results": {"text": "{\"company\":{\"transcription\":\"Abegg & Cie.\"},\"location\":{\"transcription\":\"Z\u00fcrich\"},\"b_id\":{\"transcription\":\"B.51.322.GB.266\"},\"date\":\"\",\"information\":[{\"transcription\":\"\"}]}", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct", "provider": "huggingface", "finish_reason": "stop", "usage": {"input_tokens": 2554, "output_tokens": 74, "total_tokens": 2628, "input_cost_usd": 0.0005108, "output_cost_usd": 6.512e-05, "estimated_cost_usd": 0.00057592}, "duration": 4.2896950244903564, "timestamp": "2026-08-15T21:48:59.903536", "parsed": {"company": {"transcription": "Abegg & Cie."}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.266"}, "date": "", "information": [{"transcription": ""}]}, "conversation_id": "2fd3687d-dfe9-4c2e-a866-42d9e80b8cd1", "score": {"fuzzy": 0.8}, "raw_response": "{\"id\":\"chatcmpl-RIGE1tFMuKiM9n5ijOEkoJfG\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"company\\\": {\\\"transcription\\\": \\\"Abegg & Cie.\\\"},\\n  \\\"location\\\": {\\\"transcription\\\": \\\"Z\u00fcrich\\\"},\\n  \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.266\\\"},\\n  \\\"date\\\": \\\"\\\",\\n  \\\"information\\\": [\\n    {\\\"transcription\\\": \\\"\\\"}\\n  ]\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"parsed\":{\"company\":{\"transcription\":\"Abegg & Cie.\"},\"location\":{\"transcription\":\"Z\u00fcrich\"},\"b_id\":{\"transcription\":\"B.51.322.GB.266\"},\"date\":\"\",\"information\":[{\"transcription\":\"\"}]},\"reasoning_content\":null,\"name\":null}}],\"created\":1786823340,\"model\":\"Qwen/Qwen3-VL-235B-A22B-Instruct\",\"object\":\"chat.completion\",\"service_tier\":\"default\",\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":74,\"prompt_tokens\":2554,\"total_tokens\":2628,\"completion_tokens_details\":null,\"prompt_tokens_details\":null,\"estimated_cost\":0.0005759200000000001}}"}, "scoring": {"fuzzy": 0.8332786950173297, "cost_summary": {"total_input_tokens": 84698, "total_output_tokens": 4570, "total_tokens": 89268, "input_cost_usd": 0.0169396, "output_cost_usd": 0.0040216, "total_cost_usd": 0.020961200000000003}}, "normalized_score": 83.32786950173296}