{"_id": {"$oid": "6a26c67c3572c06bc1455ee1"}, "test_id": "T1122", "benchmark": "blacklist_cards", "date": "2026-06-05", "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": "meta-llama/llama-4-scout", "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\":\"P.i.a.g. A.G.\"},\"location\":{\"transcription\":\"Luzern\"},\"b_id\":{\"transcription\":\"B.51.322.GB.970.\"},\"date\":\"1943-04-05\",\"information\":[{\"transcription\":\"Britische schwarze Liste,\\\\nAmendment 5, April 1943.\"},{\"transcription\":\"gestrichen:\\\\nAmendment 13, 23.11.1945.\"}]}", "model": "meta-llama/llama-4-scout-17b-16e-instruct", "provider": "openrouter", "finish_reason": "stop", "usage": {"input_tokens": 2914, "output_tokens": 124, "total_tokens": 3038, "estimated_cost_usd": 0.00027032, "input_cost_usd": 0.00023312, "output_cost_usd": 3.72e-05}, "duration": 694.3021123409271, "timestamp": "2026-06-05T13:08:34.269192", "parsed": {"company": {"transcription": "P.i.a.g. A.G."}, "location": {"transcription": "Luzern"}, "b_id": {"transcription": "B.51.322.GB.970."}, "date": "1943-04-05", "information": [{"transcription": "Britische schwarze Liste,\\nAmendment 5, April 1943."}, {"transcription": "gestrichen:\\nAmendment 13, 23.11.1945."}]}, "conversation_id": "20c85fe5-dd62-4954-be9e-6796c22b8a2e", "score": {"fuzzy": 0.7800495049504951}, "raw_response": "{\"id\":\"gen-1780657711-ZpdpuTwo9Dz1gWnKinCR\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"company\\\": {\\\"transcription\\\": \\\"P.i.a.g. A.G.\\\"},\\n  \\\"location\\\": {\\\"transcription\\\": \\\"Luzern\\\"},\\n  \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.970.\\\"},\\n  \\\"date\\\": \\\"1943-04-05\\\",\\n  \\\"information\\\": [\\n    {\\\"transcription\\\": \\\"Britische schwarze Liste,\\\\\\\\nAmendment 5, April 1943.\\\"},\\n    {\\\"transcription\\\": \\\"gestrichen:\\\\\\\\nAmendment 13, 23.11.1945.\\\"}\\n  ]\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"reasoning\":null},\"native_finish_reason\":\"stop\"}],\"created\":1780657711,\"model\":\"meta-llama/llama-4-scout-17b-16e-instruct\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":124,\"prompt_tokens\":2914,\"total_tokens\":3038,\"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\":0.00027032,\"is_byok\":false,\"cost_details\":{\"upstream_inference_cost\":0.00027032,\"upstream_inference_prompt_cost\":0.00023312,\"upstream_inference_completions_cost\":0.0000372}},\"provider\":\"DeepInfra\"}"}, "scoring": {"fuzzy": 0.7849181126866687, "cost_summary": {"total_input_tokens": 87332, "total_output_tokens": 4061, "total_tokens": 91393, "input_cost_usd": 0.0069865599999999976, "output_cost_usd": 0.0012182999999999999, "total_cost_usd": 0.00820486}}, "normalized_score": 78.49181126866686}