{"_id": {"$oid": "69d4eb12b877594bc5718d50"}, "test_id": "T0847", "benchmark": "blacklist_cards", "date": "2026-03-25", "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": "alibaba", "model": "qwen3.5-27b", "dataclass": "Card", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "rules": "{\"base_url\": \"https://ws-wkjpbv6ov7sqlgqe.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1\"}", "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\":\"Spuhler Clemens,\"},\"location\":{\"transcription\":\"Z\u00fcrich.\"},\"b_id\":{\"transcription\":\"B.51.322.GB.1263.\"},\"date\":\"\",\"information\":[{\"transcription\":\"Britische schwarze Liste,\\nAmendment 2, Februar 1944.\"},{\"transcription\":\"gestrichen:\\nAmendment 13, 23.11.1945.\"}]}", "model": "qwen3.5-27b", "provider": "alibaba", "finish_reason": "stop", "usage": {"input_tokens": 2896, "output_tokens": 162, "total_tokens": 3058, "input_cost_usd": 0.0008688, "output_cost_usd": 0.0003888, "estimated_cost_usd": 0.0012576}, "duration": 15.142254829406738, "timestamp": "2026-03-25T10:24:16.760325", "parsed": {"company": {"transcription": "Spuhler Clemens,"}, "location": {"transcription": "Z\u00fcrich."}, "b_id": {"transcription": "B.51.322.GB.1263."}, "date": "", "information": [{"transcription": "Britische schwarze Liste,\nAmendment 2, Februar 1944."}, {"transcription": "gestrichen:\nAmendment 13, 23.11.1945."}]}, "conversation_id": "dc2ec258-204f-46bd-ae6a-18340415d126", "score": {"fuzzy": 0.9818031430934657}, "raw_response": "{\"id\":\"chatcmpl-b4dc509c-0c83-9f8f-a383-83307fd5e997\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"company\\\": {\\n    \\\"transcription\\\": \\\"Spuhler Clemens,\\\"\\n  },\\n  \\\"location\\\": {\\n    \\\"transcription\\\": \\\"Z\u00fcrich.\\\"\\n  },\\n  \\\"b_id\\\": {\\n    \\\"transcription\\\": \\\"B.51.322.GB.1263.\\\"\\n  },\\n  \\\"date\\\": \\\"\\\",\\n  \\\"information\\\": [\\n    {\\n      \\\"transcription\\\": \\\"Britische schwarze Liste,\\\\nAmendment 2, Februar 1944.\\\"\\n    },\\n    {\\n      \\\"transcription\\\": \\\"gestrichen:\\\\nAmendment 13, 23.11.1945.\\\"\\n    }\\n  ]\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"reasoning_content\":\"\"}}],\"created\":1774430657,\"model\":\"qwen3.5-27b\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":162,\"prompt_tokens\":2896,\"total_tokens\":3058,\"completion_tokens_details\":{\"accepted_prediction_tokens\":null,\"audio_tokens\":null,\"reasoning_tokens\":null,\"rejected_prediction_tokens\":null,\"text_tokens\":162},\"prompt_tokens_details\":{\"audio_tokens\":null,\"cached_tokens\":null,\"image_tokens\":2282,\"text_tokens\":614}}}"}, "scoring": {"fuzzy": 0.9453675744203263, "cost_summary": {"total_input_tokens": 96512, "total_output_tokens": 5347, "total_tokens": 101859, "input_cost_usd": 0.0289536, "output_cost_usd": 0.012832800000000002, "total_cost_usd": 0.041786399999999994}}, "normalized_score": 94.53675744203262}