{"_id": {"$oid": "69d4eb12b877594bc5718a12"}, "test_id": "T0393", "benchmark": "company_lists", "date": "2025-10-28", "tags": {"document-type": ["book-page"], "writing": ["printed"], "century": [20], "language": ["en", "de"], "layout": ["list"], "entry-type": ["company"], "task": ["information-extraction"]}, "contributors": ["lea_kasper", "sorin_marti"], "hidden": false, "config": {"provider": "openrouter", "model": "qwen/qwen3-vl-8b-thinking", "dataclass": "ListPage", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "The image you are presented with stems from a digitized book containing lists of companies.\nYour task is to extract structured information about each company listed on the page.\n\nAbout the source:\n- The image stems from a trade index of the British Swiss Chamber of Commerce.\n- The image can show an alphabetical or a thematic list of companies.\n- The companies are mostly located in Switzerland and the UK.\n- The image stems from a trade index between 1925 and 1958.\n- Most pages have one column but some years have two columns.\n- The source itself is in English and German but the company names can be in English, German, French or Italian.\n\nAbout the entries:\n- Each entry describes a single company or person.\n- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.\n- Alphabetical entries seldom to never have locations.\n- Thematic entries often have locations.\n- Thematic entries are listed under headings that describe the type of business.\n- Some thematic headings are only references to other headings, e.g. \"X, s. Y\".\n\nAbout the output:\n- Answer in valid JSON. The JSON should be an array of objects with the following fields:\n- The page ID is given as {page_id}.\n- Do not add country information, if it is not directly written with the location.\n\n{\n  \"entry_id\": \"A unique identifier for the entry, e.g. '{page_id}-1'\",\n  \"company_name\": \"The name of the company or person\",\n  \"location\": \"The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null.\"\n  ]\n}\n", "results": {"provider": "openrouter", "model": "qwen/qwen3-vl-8b-thinking", "duration": 193.9380476474762, "timestamp": "2025-10-28T14:40:06.436598", "text": "", "raw_response": {"id": "gen-1761658786-XODL6uIZngk3FEF5Laua", "model": "qwen/qwen3-vl-8b-thinking", "choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "", "role": "assistant"}}], "usage": {"prompt_tokens": 1992, "completion_tokens": 974, "total_tokens": 2966}}, "usage": {"input_tokens": 1992, "output_tokens": 974, "total_tokens": 2966}, "error": "JSONDecodeError", "error_message": "Expecting value: line 1 column 1 (char 0)", "finish_reason": "stop"}, "scoring": {"f1_micro": 0.05103969754253308, "f1_macro": 0.034666666666666665, "micro_precision": 0.4090909090909091, "micro_recall": 0.02721774193548387, "total_instances": 15, "total_tp": 27, "total_fp": 39, "total_fn": 965, "cost_summary": {"total_input_tokens": 27657, "total_output_tokens": 21842, "total_tokens": 49499, "input_cost_usd": 0.004978, "output_cost_usd": 0.045868, "total_cost_usd": 0.050846, "pricing_date": "2025-10-28", "input_price_per_million": 0.18, "output_price_per_million": 2.1}}, "normalized_score": 3.4666666666666663}