{"_id": {"$oid": "6abd11422c9d37fedb8af875"}, "test_id": "T0977", "benchmark": "blacklist_cards", "date": "2026-04-21", "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": "openrouter", "model": "qwen/qwen3.5-flash-02-23", "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\":[]}", "model": "qwen/qwen3.5-flash-20260224", "provider": "openrouter", "finish_reason": "stop", "usage": {"input_tokens": 2951, "output_tokens": 72, "total_tokens": 3023, "input_cost_usd": 0.00019181500000000002, "output_cost_usd": 1.872e-05, "estimated_cost_usd": 0.00021053500000000003}, "duration": 3.130491018295288, "timestamp": "2026-04-21T13:42:16.469551", "parsed": {"company": {"transcription": "Abegg & Cie."}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.266"}, "date": "", "information": []}, "conversation_id": "d28c155e-de17-41cc-be3b-f752194ee757", "score": {"fuzzy": 0.8}, "raw_response": "{\"id\":\"gen-1776771733-s7nCtrNUfR14Sa52kg37\",\"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}\",\"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\":[]},\"reasoning\":null},\"native_finish_reason\":\"stop\"}],\"created\":1776771733,\"model\":\"qwen/qwen3.5-flash-20260224\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":72,\"prompt_tokens\":2951,\"total_tokens\":3023,\"completion_tokens_details\":{\"accepted_prediction_tokens\":null,\"audio_tokens\":0,\"reasoning_tokens\":0,\"rejected_prediction_tokens\":null,\"image_tokens\":0},\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":0,\"cache_write_tokens\":0,\"video_tokens\":0},\"cost\":0.000210535,\"is_byok\":false,\"cost_details\":{\"upstream_inference_cost\":0.000210535,\"upstream_inference_prompt_cost\":0.000191815,\"upstream_inference_completions_cost\":0.00001872}},\"provider\":\"Alibaba\"}"}, "scoring": {"fuzzy": 0.9198563028816031, "cost_summary": {"total_input_tokens": 97799, "total_output_tokens": 5468, "total_tokens": 103267, "input_cost_usd": 0.006356935000000002, "output_cost_usd": 0.0014216800000000005, "total_cost_usd": 0.007778615000000001}}, "pricing": {"bucket_date": "2026-04-21", "age_days": 0, "input_price_per_million": 0.065, "output_price_per_million": 0.26}, "timing": {"total_response_s": 101.24, "mean_response_s": 3.07, "slowest_response_s": 4.24, "inputs_timed": 33, "inputs_stored": 33, "span_s": 3.76}, "normalized_score": 91.98563028816031}