{"_id": {"$oid": "6acf4720ef3fcc24140a80aa"}, "test_id": "T1577", "benchmark": "blacklist_cards", "date": "2026-08-16", "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": "meta-models/Muse-Glimmer-30B:together", "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": "meta-models/Muse-Glimmer-30B", "provider": "huggingface", "finish_reason": "stop", "usage": {"input_tokens": 3219, "output_tokens": 654, "total_tokens": 3873, "cached_tokens": 256, "input_cost_usd": 0.0011266499999999999, "output_cost_usd": 0.0009809999999999999, "estimated_cost_usd": 0.00210765}, "duration": 9.139873266220093, "timestamp": "2026-08-16T02:51:52.186011", "parsed": {"company": {"transcription": "Abegg & Cie."}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.266"}, "date": "", "information": []}, "conversation_id": "41848a34-a83d-43a7-8ada-258ebfdd3568", "score": {"fuzzy": 0.8}, "raw_response": "{\"id\":\"owN4mTH-7ArivV-a2bc73c6389282e7\",\"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\":\"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.\\n\\nThe card shows \\\"A b e g g & Cie.\\\" top left. Company name? Probably \\\"Abegg & Cie.\\\" The spacing is weird with spaces between letters. Transcription should be as seen? Might be \\\"A b e g g & Cie.\\\" or \\\"Abegg & Cie.\\\" Probably transcribe as it appears: \\\"A b e g g & Cie.\\\" Might normalize? Usually transcription is literal. Could keep spaces. Maybe \\\"Abegg & Cie.\\\" I'll output \\\"Abegg & Cie.\\\" Might be safe to preserve spacing? The instruction says transcription. I'd give \\\"Abegg & Cie.\\\" The image shows spaced letters.\\n\\nLocation: Z\u00fcrich\\n\\nb_id: B.51.322.GB.266\\n\\ndate: no date, empty string.\\n\\ninformation: main body is empty. So list with one empty transcription? Or empty list? Format shows list of objects with transcription. If no information, maybe empty list [] or list with empty transcription? Probably empty list. Could provide empty list. Might need at least one empty string. Safer to provide empty list: \\\"information\\\": [].\\n\\nBut format example shows [{\\\"transcription\\\": \\\"\\\"}]. Hmm ambiguous. Might be empty list. I'll output empty list.\\n\\nLet's produce JSON.\\n\\n{\\n  \\\"company\\\": {\\\"transcription\\\": \\\"Abegg & Cie.\\\"},\\n  \\\"location\\\": {\\\"transcription\\\": \\\"Z\u00fcrich\\\"},\\n  \\\"b_id\\\": {\\\"transcription\\\": \\\"B.51.322.GB.266\\\"},\\n  \\\"date\\\": \\\"\\\",\\n  \\\"information\\\": []\\n}\\n\\nIf they expect a placeholder, maybe information with empty transcription. Could do [{\\\"transcription\\\": \\\"\\\"}]. Might be okay.\\n\\nI'll choose empty list.\\n\\nReturn only JSON.\"},\"token_ids\":null,\"routed_experts\":null,\"seed\":null}],\"created\":1786841504,\"model\":\"meta-models/Muse-Glimmer-30B\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":\"vllm-0.1.dev19059+g66826a22d-tp2-46311a71\",\"usage\":{\"completion_tokens\":654,\"prompt_tokens\":3219,\"total_tokens\":3873,\"completion_tokens_details\":null,\"prompt_tokens_details\":{\"audio_tokens\":null,\"cached_tokens\":256,\"created_cache_tokens\":2960,\"multimodal_tokens\":{\"image\":2946}}},\"prompt_token_ids\":null,\"prompt_text\":null,\"kv_transfer_params\":null,\"ec_transfer_params\":null,\"metrics\":null,\"prompt\":[]}"}, "scoring": {"fuzzy": 0.9408690199005607, "cost_summary": {"total_input_tokens": 108615, "total_output_tokens": 30606, "total_tokens": 139221, "input_cost_usd": 0.038015249999999993, "output_cost_usd": 0.045909000000000005, "total_cost_usd": 0.08392424999999998}}, "pricing": {"bucket_date": "2026-08-15", "age_days": 1, "input_price_per_million": 0.35, "output_price_per_million": 1.5}, "timing": {"total_response_s": 358.69, "mean_response_s": 10.87, "slowest_response_s": 15.83, "inputs_timed": 33, "inputs_stored": 33, "span_s": 115.41}, "normalized_score": 94.08690199005608}