{"_id": {"$oid": "6a2bd2517c8509fc28cb4288"}, "test_id": "T1016", "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": "google/gemma-4-31b-it", "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\":\"Skiff A.G.,\"},\"location\":{\"transcription\":\"Luzern\"},\"b_id\":{\"transcription\":\"B.51.322.GB.976.\"},\"date\":\"1943-04-01\",\"information\":[{\"transcription\":\"Britische schwarze Liste,\\nAmendment 5, April 1943.\"},{\"transcription\":\"gestrichen:\\nAmendment 3, M\u00e4rz 1944.\"}]}", "model": "google/gemma-4-31b-it-20260402", "provider": "openrouter", "finish_reason": "stop", "usage": {"input_tokens": 570, "output_tokens": 116, "total_tokens": 686, "input_cost_usd": 7.41e-05, "output_cost_usd": 4.408e-05, "estimated_cost_usd": 0.00011818}, "duration": 3.484691619873047, "timestamp": "2026-04-21T17:00:49.189143", "parsed": {"company": {"transcription": "Skiff A.G.,"}, "location": {"transcription": "Luzern"}, "b_id": {"transcription": "B.51.322.GB.976."}, "date": "1943-04-01", "information": [{"transcription": "Britische schwarze Liste,\nAmendment 5, April 1943."}, {"transcription": "gestrichen:\nAmendment 3, M\u00e4rz 1944."}]}, "conversation_id": "4b83122d-5378-49a8-99f2-35f05ae1438e", "score": {"fuzzy": 0.8253968253968255}, "raw_response": "{\"id\":\"gen-1776783645-SM8ntF7JDbnePz7TZlnT\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\\"company\\\": {\\\"transcription\\\": \\\"Skiff A.G.,\\\"}, \\\"location\\\": {\\\"transcription\\\": \\\"Luzern\\\"}, \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.976.\\\"}, \\\"date\\\": \\\"1943-04-01\\\", \\\"information\\\": [{\\\"transcription\\\": \\\"Britische schwarze Liste,\\\\nAmendment 5, April 1943.\\\"}, {\\\"transcription\\\": \\\"gestrichen:\\\\nAmendment 3, M\u00e4rz 1944.\\\"}]}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"parsed\":{\"company\":{\"transcription\":\"Skiff A.G.,\"},\"location\":{\"transcription\":\"Luzern\"},\"b_id\":{\"transcription\":\"B.51.322.GB.976.\"},\"date\":\"1943-04-01\",\"information\":[{\"transcription\":\"Britische schwarze Liste,\\nAmendment 5, April 1943.\"},{\"transcription\":\"gestrichen:\\nAmendment 3, M\u00e4rz 1944.\"}]},\"reasoning\":null},\"native_finish_reason\":\"stop\"}],\"created\":1776783645,\"model\":\"google/gemma-4-31b-it-20260402\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":116,\"prompt_tokens\":570,\"total_tokens\":686,\"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\":0.000172,\"is_byok\":false,\"cost_details\":{\"upstream_inference_cost\":0.000172,\"upstream_inference_prompt_cost\":0.000114,\"upstream_inference_completions_cost\":0.000058}},\"provider\":\"Together\"}"}, "scoring": {"fuzzy": 0.9053185546570406, "cost_summary": {"total_input_tokens": 20454, "total_output_tokens": 4782, "total_tokens": 25236, "input_cost_usd": 0.00265902, "output_cost_usd": 0.00181716, "total_cost_usd": 0.00447618}}, "normalized_score": 90.53185546570406}