{"_id": {"$oid": "69d4eb12b877594bc5718be5"}, "test_id": "T0574", "benchmark": "company_lists", "date": "2026-01-25", "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": "mistral", "model": "magistral-small-2509", "dataclass": "ListPage", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt_min.txt", "legacy_test": false}, "prompt": "- Answer in valid JSON.\n- The page ID is given as {page_id}.\n", "results": {"text": "{\"page_id\":\"{page_id}\",\"entries\":[]}", "model": "magistral-small-2509", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 198, "output_tokens": 23, "total_tokens": 221, "input_cost_usd": 9.9e-05, "output_cost_usd": 1.15e-05, "estimated_cost_usd": 0.00011049999999999999}, "duration": 0.44805479049682617, "timestamp": "2026-01-25T01:55:45.663366", "parsed": {"page_id": "{page_id}", "entries": []}, "conversation_id": "d71f725c-023d-4700-aafc-868a86caacf9", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 1, "false_negatives": 65, "field_scores": {"entries[25].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[5].company_name": {"response": "", "ground_truth": "Basler M\u00f6belfabrik A.-G. vorm. Hermann Wagner & Cie.", "score": 0.0}, "entries[19].company_name": {"response": "", "ground_truth": "Hug & Co.", "score": 0.0}, "entries[29].entry_id": {"response": "", "ground_truth": "156089_1321079_26-30", "score": 0.0}, "entries[13].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[10].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[8].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[19].entry_id": {"response": "", "ground_truth": "156089_1321079_26-20", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "M. Russ", "score": 0.0}, "entries[13].entry_id": {"response": "", "ground_truth": "156089_1321079_26-14", "score": 0.0}, "entries[29].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[28].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[20].entry_id": {"response": "", "ground_truth": "156089_1321079_26-21", "score": 0.0}, "entries[21].entry_id": {"response": "", "ground_truth": "156089_1321079_26-22", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321079_26-5", "score": 0.0}, "entries[0].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[26].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321079_26-3", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321079_26-6", "score": 0.0}, "entries[12].entry_id": {"response": "", "ground_truth": "156089_1321079_26-13", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "Singer & Buchenhorner A.-G.", "score": 0.0}, "entries[16].entry_id": {"response": "", "ground_truth": "156089_1321079_26-17", "score": 0.0}, "entries[20].location": {"response": "", "ground_truth": "Liestal", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "H. Hartmann", "score": 0.0}, "entries[24].entry_id": {"response": "", "ground_truth": "156089_1321079_26-25", "score": 0.0}, "entries[17].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[23].entry_id": {"response": "", "ground_truth": "156089_1321079_26-24", "score": 0.0}, "entries[18].entry_id": {"response": "", "ground_truth": "156089_1321079_26-19", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "Fr\u00e4nkel & Voellmy", "score": 0.0}, "entries[21].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321079_26-7", "score": 0.0}, "entries[14].entry_id": {"response": "", "ground_truth": "156089_1321079_26-15", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[10].company_name": {"response": "", "ground_truth": "Kunsthandlung Rath", "score": 0.0}, "entries[13].company_name": {"response": "", "ground_truth": "Wolf & Glatz", "score": 0.0}, "page_id": {"response": "{page_id}", "ground_truth": "156089_1321079_26", "score": 0.07692307692307687}, "entries[19].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[1].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[20].company_name": {"response": "", "ground_truth": "Schweiz. Geigenbaugesellschaft Liestal", "score": 0.0}, "entries[18].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[30].company_name": {"response": "", "ground_truth": "E. H. Schacke", "score": 0.0}, "entries[22].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[25].company_name": {"response": "", "ground_truth": "Ch. H. Pfister & Co.", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[26].entry_id": {"response": "", "ground_truth": "156089_1321079_26-27", "score": 0.0}, "entries[24].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[6].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[28].entry_id": {"response": "", "ground_truth": "156089_1321079_26-29", "score": 0.0}, "entries[0].entry_id": {"response": "", "ground_truth": "156089_1321079_26-1", "score": 0.0}, "entries[15].company_name": {"response": "", "ground_truth": "A.-G. B\u00e4chtold & Cie.", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321079_26-10", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[3].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[25].entry_id": {"response": "", "ground_truth": "156089_1321079_26-26", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321079_26-8", "score": 0.0}, "entries[0].company_name": {"response": "", "ground_truth": "A. Boreux", "score": 0.0}, "entries[16].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[12].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321079_26-11", "score": 0.0}, "entries[18].company_name": {"response": "", "ground_truth": "A.-G. f\u00fcr Motorlastwagen Soller", "score": 0.0}, "entries[28].company_name": {"response": "", "ground_truth": "Schweizerische N\u00e4hmaschinenfabrik A.-G.", "score": 0.0}, "entries[16].company_name": {"response": "", "ground_truth": "Maschinenfabrik Burckhardt A.-G.", "score": 0.0}, "entries[26].company_name": {"response": "", "ground_truth": "E. M\u00fcry & Cie.", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321079_26-9", "score": 0.0}, "entries[29].company_name": {"response": "", "ground_truth": "G. P. Richter", "score": 0.0}, "entries[27].location": {"response": "", "ground_truth": "Niederdorf", "score": 0.0}, "entries[30].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[6].company_name": {"response": "", "ground_truth": "Adolf B\u00fcrgin", "score": 0.0}, "entries[14].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[24].company_name": {"response": "", "ground_truth": "Alb. Singeisen-Halder", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Alf. D\u00fcrr, J. H. Neukomm's Nachf.", "score": 0.0}, "entries[17].company_name": {"response": "", "ground_truth": "G. Meidinger & Cie.", "score": 0.0}, "entries[21].company_name": {"response": "", "ground_truth": "Schweizerisches Musikhaus Bannwart & Cie.", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[15].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[27].entry_id": {"response": "", "ground_truth": "156089_1321079_26-28", "score": 0.0}, "entries[27].company_name": {"response": "", "ground_truth": "Affentranger, Haas & Plattner", "score": 0.0}, "entries[1].company_name": {"response": "", "ground_truth": "Brunnenverwaltung Eptingen", "score": 0.0}, "entries[4].company_name": {"response": "", "ground_truth": "Ausstattungsmagazine Ed. Senft.", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Bussinger & Cie.", "score": 0.0}, "entries[23].company_name": {"response": "", "ground_truth": "Hans Ritter-Soder", "score": 0.0}, "entries[22].entry_id": {"response": "", "ground_truth": "156089_1321079_26-23", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[17].entry_id": {"response": "", "ground_truth": "156089_1321079_26-18", "score": 0.0}, "entries[23].location": {"response": "", "ground_truth": "", "score": 1.0}, "entries[30].entry_id": {"response": "", "ground_truth": "156089_1321079_26-31", "score": 0.0}, "entries[12].company_name": {"response": "", "ground_truth": "Alf. Schray", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321079_26-12", "score": 0.0}, "entries[22].company_name": {"response": "", "ground_truth": "Henri Grunauer", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321079_26-4", "score": 0.0}, "entries[1].entry_id": {"response": "", "ground_truth": "156089_1321079_26-2", "score": 0.0}, "entries[14].company_name": {"response": "", "ground_truth": "Gebr. Antonietti", "score": 0.0}, "entries[15].entry_id": {"response": "", "ground_truth": "156089_1321079_26-16", "score": 0.0}}, "total_fields": 94}, "raw_response": "{\"id\":\"cdccee96a36b4df5816e58545812fa5d\",\"object\":\"chat.completion\",\"model\":\"magistral-small-2509\",\"usage\":{\"prompt_tokens\":198,\"completion_tokens\":23,\"total_tokens\":221,\"num_cached_tokens\":128},\"created\":1769302545,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{  \\n  \\\"page_id\\\": \\\"{page_id}\\\",  \\n  \\\"entries\\\": []  \\n}\",\"tool_calls\":null,\"prefix\":false,\"role\":\"assistant\"},\"finish_reason\":\"stop\"}]}"}, "scoring": {"f1_micro": 0.0, "f1_macro": 0.0, "micro_precision": 0.0, "micro_recall": 0.0, "total_instances": 15, "total_tp": 0, "total_fp": 31, "total_fn": 992, "cost_summary": {"total_input_tokens": 2970, "total_output_tokens": 1733, "total_tokens": 4703, "input_cost_usd": 0.0014849999999999996, "output_cost_usd": 0.0008665000000000001, "total_cost_usd": 0.0023515000000000003}}, "normalized_score": 0}