{"_id": {"$oid": "69d4eb12b877594bc5718d2c"}, "test_id": "T0823", "benchmark": "company_lists", "date": "2026-03-24", "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": "alibaba", "model": "qwen3.5-plus-2026-02-15", "dataclass": "ListPage", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt_min.txt", "rules": "{\"base_url\": \"https://ws-wkjpbv6ov7sqlgqe.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1\"}", "legacy_test": false}, "prompt": "- Answer in valid JSON.\n- The page ID is given as {page_id}.\n", "results": {"text": "{\"page_id\":\"9\",\"entries\":[{\"entry_id\":\"1\",\"company_name\":\"Crowe & Co., Ltd.\",\"location\":\"Basle\"},{\"entry_id\":\"2\",\"company_name\":\"Imperial Airways Ltd.\",\"location\":\"Croydon\"},{\"entry_id\":\"3\",\"company_name\":\"Metallwerke A.G.\",\"location\":\"Dornach (Solothurn)\"},{\"entry_id\":\"4\",\"company_name\":\"Aluminium-Industrie-Aktien-Gesellschaft\",\"location\":\"Neuhausen\"},{\"entry_id\":\"5\",\"company_name\":\"Chemische Fabrik vorm. Sandoz\",\"location\":\"Basle\"},{\"entry_id\":\"6\",\"company_name\":\"Clayton Aniline Co., Ltd.\",\"location\":\"Manchester\"},{\"entry_id\":\"7\",\"company_name\":\"J. R. Geigy, A.-G.\",\"location\":\"Basle\"},{\"entry_id\":\"8\",\"company_name\":\"Society of Chemical Industry in Basle\",\"location\":\"Basle\"},{\"entry_id\":\"9\",\"company_name\":\"J. Hopf & Co.\",\"location\":\"Basle\"},{\"entry_id\":\"10\",\"company_name\":\"Rayon A.-G.\",\"location\":\"Arlesheim\"},{\"entry_id\":\"11\",\"company_name\":\"Banque F\u00e9d\u00e9rale S.A.\",\"location\":\"Vevey\"},{\"entry_id\":\"12\",\"company_name\":\"Barclays Bank Ltd.\",\"location\":\"London E.C. 3\"},{\"entry_id\":\"13\",\"company_name\":\"Galland & Co.\",\"location\":\"Lausanne\"},{\"entry_id\":\"14\",\"company_name\":\"Lloyds and National Provincial Foreign Bank, Ltd.\",\"location\":\"Geneva\"},{\"entry_id\":\"15\",\"company_name\":\"Swiss Bank Corporation\",\"location\":\"Basle\"},{\"entry_id\":\"16\",\"company_name\":\"Swiss Bank Corporation\",\"location\":\"Lausanne\"},{\"entry_id\":\"17\",\"company_name\":\"Wagons-Lits/Cook S.A.\",\"location\":\"Geneva\"}]}", "model": "qwen3.5-plus", "provider": "alibaba", "finish_reason": "stop", "usage": {"input_tokens": 2715, "output_tokens": 702, "total_tokens": 3417, "input_cost_usd": 0.001086, "output_cost_usd": 0.0016848, "estimated_cost_usd": 0.0027708}, "duration": 19.957101345062256, "timestamp": "2026-03-24T22:09:23.840448", "parsed": {"page_id": "9", "entries": [{"entry_id": "1", "company_name": "Crowe & Co., Ltd.", "location": "Basle"}, {"entry_id": "2", "company_name": "Imperial Airways Ltd.", "location": "Croydon"}, {"entry_id": "3", "company_name": "Metallwerke A.G.", "location": "Dornach (Solothurn)"}, {"entry_id": "4", "company_name": "Aluminium-Industrie-Aktien-Gesellschaft", "location": "Neuhausen"}, {"entry_id": "5", "company_name": "Chemische Fabrik vorm. Sandoz", "location": "Basle"}, {"entry_id": "6", "company_name": "Clayton Aniline Co., Ltd.", "location": "Manchester"}, {"entry_id": "7", "company_name": "J. R. Geigy, A.-G.", "location": "Basle"}, {"entry_id": "8", "company_name": "Society of Chemical Industry in Basle", "location": "Basle"}, {"entry_id": "9", "company_name": "J. Hopf & Co.", "location": "Basle"}, {"entry_id": "10", "company_name": "Rayon A.-G.", "location": "Arlesheim"}, {"entry_id": "11", "company_name": "Banque F\u00e9d\u00e9rale S.A.", "location": "Vevey"}, {"entry_id": "12", "company_name": "Barclays Bank Ltd.", "location": "London E.C. 3"}, {"entry_id": "13", "company_name": "Galland & Co.", "location": "Lausanne"}, {"entry_id": "14", "company_name": "Lloyds and National Provincial Foreign Bank, Ltd.", "location": "Geneva"}, {"entry_id": "15", "company_name": "Swiss Bank Corporation", "location": "Basle"}, {"entry_id": "16", "company_name": "Swiss Bank Corporation", "location": "Lausanne"}, {"entry_id": "17", "company_name": "Wagons-Lits/Cook S.A.", "location": "Geneva"}]}, "conversation_id": "63324a3b-c560-4c7f-87bb-48f0fd830ad4", "score": {"f1_score": 0.6, "precision": 0.5961538461538461, "recall": 0.5961538461538461, "true_positives": 31, "false_positives": 21, "false_negatives": 21, "field_scores": {"entries[15].entry_id": {"response": "16", "ground_truth": "156089_1321093_11-16", "score": 0.18181818181818177}, "entries[0].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[9].company_name": {"response": "Rayon A.-G.", "ground_truth": "Rayon A.-G. (Merchants)", "score": 0.6470588235294117}, "entries[11].location": {"response": "London E.C. 3", "ground_truth": "London E.C. 3.", "score": 0.962962962962963}, "entries[13].location": {"response": "Geneva", "ground_truth": "Geneva", "score": 1.0}, "entries[15].location": {"response": "Lausanne", "ground_truth": "Lausanne", "score": 1.0}, "entries[4].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[12].company_name": {"response": "Galland & Co.", "ground_truth": "Galland & Co.", "score": 1.0}, "entries[6].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[14].company_name": {"response": "Swiss Bank Corporation", "ground_truth": "Swiss Bank Corporation", "score": 1.0}, "entries[7].entry_id": {"response": "8", "ground_truth": "156089_1321093_11-8", "score": 0.09999999999999998}, "entries[15].company_name": {"response": "Swiss Bank Corporation", "ground_truth": "Swiss Bank Corporation", "score": 1.0}, "entries[16].location": {"response": "Geneva", "ground_truth": "Geneva", "score": 1.0}, "entries[7].company_name": {"response": "Society of Chemical Industry in Basle", "ground_truth": "Society of Chemical Industry in Basle", "score": 1.0}, "entries[1].location": {"response": "Croydon", "ground_truth": "Croydon", "score": 1.0}, "entries[11].company_name": {"response": "Barclays Bank Ltd.", "ground_truth": "Barclays Bank Ltd. (Foreign Branch)", "score": 0.679245283018868}, "entries[8].company_name": {"response": "J. Hopf & Co.", "ground_truth": "J. Hopf & Co. (Merchants)", "score": 0.6842105263157895}, "entries[12].entry_id": {"response": "13", "ground_truth": "156089_1321093_11-13", "score": 0.18181818181818177}, "entries[8].entry_id": {"response": "9", "ground_truth": "156089_1321093_11-9", "score": 0.09999999999999998}, "entries[6].company_name": {"response": "J. R. Geigy, A.-G.", "ground_truth": "J. R. Geigy, A.-G.", "score": 1.0}, "entries[14].entry_id": {"response": "15", "ground_truth": "156089_1321093_11-15", "score": 0.18181818181818177}, "entries[10].location": {"response": "Vevey", "ground_truth": "Vevey", "score": 1.0}, "entries[7].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[3].entry_id": {"response": "4", "ground_truth": "156089_1321093_11-4", "score": 0.09999999999999998}, "entries[16].company_name": {"response": "Wagons-Lits/Cook S.A.", "ground_truth": "Wagons-Lits/Cook S.A.", "score": 1.0}, "page_id": {"response": "9", "ground_truth": "156089_1321093_11", "score": 0.11111111111111116}, "entries[11].entry_id": {"response": "12", "ground_truth": "156089_1321093_11-12", "score": 0.18181818181818177}, "entries[1].company_name": {"response": "Imperial Airways Ltd.", "ground_truth": "Imperial Airways Ltd.", "score": 1.0}, "entries[1].entry_id": {"response": "2", "ground_truth": "156089_1321093_11-2", "score": 0.09999999999999998}, "entries[4].entry_id": {"response": "5", "ground_truth": "156089_1321093_11-5", "score": 0.09999999999999998}, "entries[2].entry_id": {"response": "3", "ground_truth": "156089_1321093_11-3", "score": 0.09999999999999998}, "entries[4].company_name": {"response": "Chemische Fabrik vorm. Sandoz", "ground_truth": "Chemische Fabrik vorm. Sandoz", "score": 1.0}, "entries[5].location": {"response": "Manchester", "ground_truth": "Manchester", "score": 1.0}, "entries[13].company_name": {"response": "Lloyds and National Provincial Foreign Bank, Ltd.", "ground_truth": "Lloyds and National Provincial Foreign Bank, Ltd.", "score": 1.0}, "entries[14].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[2].company_name": {"response": "Metallwerke A.G.", "ground_truth": "Metallwerke A.G.", "score": 1.0}, "entries[3].location": {"response": "Neuhausen", "ground_truth": "Neuhausen", "score": 1.0}, "entries[5].company_name": {"response": "Clayton Aniline Co., Ltd.", "ground_truth": "Clayton Aniline Co., Ltd.", "score": 1.0}, "entries[16].entry_id": {"response": "17", "ground_truth": "156089_1321093_11-17", "score": 0.18181818181818177}, "entries[10].company_name": {"response": "Banque F\u00e9d\u00e9rale S.A.", "ground_truth": "Banque F\u00e9d\u00e9rale S.A.", "score": 1.0}, "entries[5].entry_id": {"response": "6", "ground_truth": "156089_1321093_11-6", "score": 0.09999999999999998}, "entries[9].location": {"response": "Arlesheim", "ground_truth": "Arlesheim", "score": 1.0}, "entries[12].location": {"response": "Lausanne", "ground_truth": "Lausanne", "score": 1.0}, "entries[3].company_name": {"response": "Aluminium-Industrie-Aktien-Gesellschaft", "ground_truth": "Aluminium-Industrie-Aktien-Gesellschaft", "score": 1.0}, "entries[13].entry_id": {"response": "14", "ground_truth": "156089_1321093_11-14", "score": 0.18181818181818177}, "entries[0].company_name": {"response": "Crowe & Co., Ltd.", "ground_truth": "Crowe & Co., Ltd.", "score": 1.0}, "entries[9].entry_id": {"response": "10", "ground_truth": "156089_1321093_11-10", "score": 0.18181818181818177}, "entries[8].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[0].entry_id": {"response": "1", "ground_truth": "156089_1321093_11-1", "score": 0.09999999999999998}, "entries[6].entry_id": {"response": "7", "ground_truth": "156089_1321093_11-7", "score": 0.09999999999999998}, "entries[2].location": {"response": "Dornach (Solothurn)", "ground_truth": "Dornach (Solothurn)", "score": 1.0}, "entries[10].entry_id": {"response": "11", "ground_truth": "156089_1321093_11-11", "score": 0.18181818181818177}}, "total_fields": 52}, "raw_response": "{\"id\":\"chatcmpl-a88a5120-0198-967e-aeae-f9684002f689\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\n  \\\"page_id\\\": \\\"9\\\",\\n  \\\"entries\\\": [\\n    {\\n      \\\"entry_id\\\": \\\"1\\\",\\n      \\\"company_name\\\": \\\"Crowe & Co., Ltd.\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"2\\\",\\n      \\\"company_name\\\": \\\"Imperial Airways Ltd.\\\",\\n      \\\"location\\\": \\\"Croydon\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"3\\\",\\n      \\\"company_name\\\": \\\"Metallwerke A.G.\\\",\\n      \\\"location\\\": \\\"Dornach (Solothurn)\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"4\\\",\\n      \\\"company_name\\\": \\\"Aluminium-Industrie-Aktien-Gesellschaft\\\",\\n      \\\"location\\\": \\\"Neuhausen\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"5\\\",\\n      \\\"company_name\\\": \\\"Chemische Fabrik vorm. Sandoz\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"6\\\",\\n      \\\"company_name\\\": \\\"Clayton Aniline Co., Ltd.\\\",\\n      \\\"location\\\": \\\"Manchester\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"7\\\",\\n      \\\"company_name\\\": \\\"J. R. Geigy, A.-G.\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"8\\\",\\n      \\\"company_name\\\": \\\"Society of Chemical Industry in Basle\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"9\\\",\\n      \\\"company_name\\\": \\\"J. Hopf & Co.\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"10\\\",\\n      \\\"company_name\\\": \\\"Rayon A.-G.\\\",\\n      \\\"location\\\": \\\"Arlesheim\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"11\\\",\\n      \\\"company_name\\\": \\\"Banque F\u00e9d\u00e9rale S.A.\\\",\\n      \\\"location\\\": \\\"Vevey\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"12\\\",\\n      \\\"company_name\\\": \\\"Barclays Bank Ltd.\\\",\\n      \\\"location\\\": \\\"London E.C. 3\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"13\\\",\\n      \\\"company_name\\\": \\\"Galland & Co.\\\",\\n      \\\"location\\\": \\\"Lausanne\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"14\\\",\\n      \\\"company_name\\\": \\\"Lloyds and National Provincial Foreign Bank, Ltd.\\\",\\n      \\\"location\\\": \\\"Geneva\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"15\\\",\\n      \\\"company_name\\\": \\\"Swiss Bank Corporation\\\",\\n      \\\"location\\\": \\\"Basle\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"16\\\",\\n      \\\"company_name\\\": \\\"Swiss Bank Corporation\\\",\\n      \\\"location\\\": \\\"Lausanne\\\"\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"17\\\",\\n      \\\"company_name\\\": \\\"Wagons-Lits/Cook S.A.\\\",\\n      \\\"location\\\": \\\"Geneva\\\"\\n    }\\n  ]\\n}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":null,\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"reasoning_content\":\"\"}}],\"created\":1774386563,\"model\":\"qwen3.5-plus\",\"object\":\"chat.completion\",\"service_tier\":null,\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":702,\"prompt_tokens\":2715,\"total_tokens\":3417,\"completion_tokens_details\":{\"accepted_prediction_tokens\":null,\"audio_tokens\":null,\"reasoning_tokens\":null,\"rejected_prediction_tokens\":null,\"text_tokens\":702},\"prompt_tokens_details\":{\"audio_tokens\":null,\"cached_tokens\":null,\"image_tokens\":2503,\"text_tokens\":212}}}"}, "scoring": {"f1_micro": 0.4509903504316912, "f1_macro": 0.45266666666666666, "micro_precision": 0.45445240532241554, "micro_recall": 0.4475806451612903, "total_instances": 15, "total_tp": 444, "total_fp": 533, "total_fn": 548, "cost_summary": {"total_input_tokens": 40921, "total_output_tokens": 14445, "total_tokens": 55366, "input_cost_usd": 0.0163684, "output_cost_usd": 0.034668000000000004, "total_cost_usd": 0.0510364}}, "normalized_score": 45.266666666666666}