{"_id": {"$oid": "6ac4c7b5164e0f17c0b234ae"}, "test_id": "T1502", "benchmark": "blacklist_cards", "date": "2026-08-14", "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-v1.5-8B: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.266\"},\"date\":\"\",\"information\":[{\"transcription\":\"Z\u00fcrich\"}]}", "model": "swiss-ai/apertus-v1.5-8b", "provider": "huggingface", "finish_reason": "stop", "usage": {"input_tokens": 7978, "output_tokens": 78, "total_tokens": 8056, "input_cost_usd": 0.0007978000000000001, "output_cost_usd": 1.56e-05, "estimated_cost_usd": 0.0008134000000000001}, "duration": 10.91163969039917, "timestamp": "2026-08-14T16:18:43.852451", "parsed": {"company": {"transcription": "Abegg & Cie."}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.266"}, "date": "", "information": [{"transcription": "Z\u00fcrich"}]}, "conversation_id": "5121b3a7-39f7-4129-bdee-8411499521b4", "score": {"fuzzy": 0.8}, "raw_response": "{\"id\":\"chatcmpl-eabbf45a-0dcb-4134-82cf-de672679a770\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.266\\\"},\\n  \\\"company\\\": {\\\"transcription\\\": \\\"Abegg & Cie.\\\"},\\n  \\\"date\\\": \\\"\\\",\\n  \\\"information\\\": [\\n    {\\\"transcription\\\": \\\"Z\u00fcrich\\\"}\\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.266\"},\"date\":\"\",\"information\":[{\"transcription\":\"Z\u00fcrich\"}]},\"provider_specific_fields\":{\"reasoning\":null,\"refusal\":null}},\"provider_specific_fields\":{\"stop_reason\":null,\"routed_experts\":null,\"token_ids\":null}}],\"created\":1786717115,\"model\":\"swiss-ai/apertus-v1.5-8b\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":\"vllm-0.23.1rc1.dev1029+ga601a9d99-2d880180\",\"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": 0.7886297783005229, "cost_summary": {"total_input_tokens": 264021, "total_output_tokens": 4399, "total_tokens": 268420, "input_cost_usd": 0.02640209999999999, "output_cost_usd": 0.0008797999999999999, "total_cost_usd": 0.027281900000000005}}, "pricing": {"bucket_date": "2026-08-10", "age_days": 4, "input_price_per_million": 0.1, "output_price_per_million": 0.2}, "timing": {"total_response_s": 555.17, "mean_response_s": 16.82, "slowest_response_s": 28.61, "inputs_timed": 33, "inputs_stored": 33, "span_s": 17.78}, "normalized_score": 78.8629778300523}