{"_id": {"$oid": "6acf4720ef3fcc24140a8090"}, "test_id": "T1487", "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": "swiss-ai/Apertus-v1.5-70B:publicai", "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.206\"},\"date\":\"\",\"information\":[{\"transcription\":\"\"}]}", "model": "swiss-ai/apertus-v1.5-70b", "provider": "huggingface", "finish_reason": "stop", "usage": {"input_tokens": 7978, "output_tokens": 78, "total_tokens": 8056, "input_cost_usd": 0.00654196, "output_cost_usd": 0.00022776, "estimated_cost_usd": 0.00676972}, "duration": 4.2558488845825195, "timestamp": "2026-08-15T04:36:43.585524", "parsed": {"company": {"transcription": "Abegg & Cie."}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.206"}, "date": "", "information": [{"transcription": ""}]}, "conversation_id": "a56d6486-51b5-4889-96d0-34eee7883dcb", "score": {"fuzzy": 0.7866666666666666}, "raw_response": "{\"id\":\"chatcmpl-736de693-88f7-4511-964e-dbd49024833d\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.206\\\"},\\n  \\\"company\\\": {\\\"transcription\\\": \\\"Abegg & Cie.\\\"},\\n  \\\"date\\\": \\\"\\\",\\n  \\\"information\\\": [\\n    {\\n      \\\"transcription\\\": \\\"\\\"\\n    }\\n  ],\\n  \\\"location\\\": {\\\"transcription\\\": \\\"Z\u00fcrich\\\"}\\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.206\"},\"date\":\"\",\"information\":[{\"transcription\":\"\"}]},\"provider_specific_fields\":{\"refusal\":null,\"reasoning\":null}},\"provider_specific_fields\":{\"stop_reason\":null,\"routed_experts\":null,\"token_ids\":null}}],\"created\":1786761401,\"model\":\"swiss-ai/apertus-v1.5-70b\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":\"vllm-0.23.1rc1.dev1029+ga601a9d99-tp4-1381023c\",\"usage\":{\"completion_tokens\":78,\"prompt_tokens\":7978,\"total_tokens\":8056,\"completion_tokens_details\":null,\"prompt_tokens_details\":{\"audio_tokens\":null,\"cached_tokens\":0,\"multimodal_tokens\":{\"image\":7704}}}}"}, "scoring": {"fuzzy": 0.832817868847714, "cost_summary": {"total_input_tokens": 264021, "total_output_tokens": 4253, "total_tokens": 268274, "input_cost_usd": 0.21649722, "output_cost_usd": 0.012418760000000001, "total_cost_usd": 0.22891597999999996}}, "pricing": {"bucket_date": "2026-08-10", "age_days": 5, "input_price_per_million": 0.82, "output_price_per_million": 2.92}, "timing": {"total_response_s": 160.01, "mean_response_s": 4.85, "slowest_response_s": 6.12, "inputs_timed": 33, "inputs_stored": 33, "span_s": 155.93}, "normalized_score": 83.2817868847714}