{"record": {"aliases": [], "artifacts": [], "categories": ["agentic", "business", "reasoning"], "description": {"en": "Quantitative analysis on spreadsheets & documents"}, "documents": [{"document_type": "registry_page", "id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "title": "AA-AnalystAgent"}], "evidence_summary": {"document_count": 1, "model_count": 30, "model_count_basis": "source_model_id"}, "key": "artificial-analysis:aa-analystagent", "modality": null, "name": "AA-AnalystAgent", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"crawl_bundle": "artificial_analysis_2026-08-25", "crawled_at": "2026-08-25T10:41:06Z", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "artificial-analysis-aa-analystagent", "source": "artificial_analysis", "source_benchmark_id": "aa-analystagent"}, "schema_version": 1, "scores_by_source": {"artificial_analysis": {"rows": [{"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "b2331108-72ed-415a-82d1-188633875bbc", "model_name": "Gemini 3.7 Flash (high)", "obs_id": "artificial_analysis:aa-analystagent:b2331108-72ed-415a-82d1-188633875bbc", "organization": "Google", "rank_in_source_response": 1, "raw_value": "0.6", "reported_by": "third_party", "reported_date": "2026-08-13", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.6, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "b8fc61f7-5e9a-49e6-8547-6ac56db24627", "model_name": "Claude Opus 5 (Adaptive Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:b8fc61f7-5e9a-49e6-8547-6ac56db24627", "organization": "Anthropic", "rank_in_source_response": 2, "raw_value": "0.5375", "reported_by": "third_party", "reported_date": "2026-07-24", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.5375, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "1f054429-397e-4fdb-9e71-67bc92c1735e", "model_name": "GPT-5.5 (xhigh)", "obs_id": "artificial_analysis:aa-analystagent:1f054429-397e-4fdb-9e71-67bc92c1735e", "organization": "OpenAI", "rank_in_source_response": 3, "raw_value": "0.5", "reported_by": "third_party", "reported_date": "2026-04-23", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.5, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "cd55210d-358e-4df1-ba9c-9acb5f186cc9", "model_name": "Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)", "obs_id": "artificial_analysis:aa-analystagent:cd55210d-358e-4df1-ba9c-9acb5f186cc9", "organization": "Anthropic", "rank_in_source_response": 4, "raw_value": "0.4875", "reported_by": "third_party", "reported_date": "2026-06-09", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.4875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "d93edfe8-bf35-49ad-b56e-b18116142a1c", "model_name": "GPT-5.6 Sol (max)", "obs_id": "artificial_analysis:aa-analystagent:d93edfe8-bf35-49ad-b56e-b18116142a1c", "organization": "OpenAI", "rank_in_source_response": 5, "raw_value": "0.475", "reported_by": "third_party", "reported_date": "2026-07-09", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.475, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "23c86e4a-c769-43c0-a056-79e3cd15834f", "model_name": "Claude Sonnet 5 (Adaptive Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:23c86e4a-c769-43c0-a056-79e3cd15834f", "organization": "Anthropic", "rank_in_source_response": 6, "raw_value": "0.4625", "reported_by": "third_party", "reported_date": "2026-06-30", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.4625, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "0097ebf5-124f-42f6-9463-33b00e711f03", "model_name": "Gemini 3.5 Flash (high)", "obs_id": "artificial_analysis:aa-analystagent:0097ebf5-124f-42f6-9463-33b00e711f03", "organization": "Google", "rank_in_source_response": 7, "raw_value": "0.45", "reported_by": "third_party", "reported_date": "2026-05-19", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.45, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "992b7b84-5069-4c6a-9295-834252553d50", "model_name": "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:992b7b84-5069-4c6a-9295-834252553d50", "organization": "Anthropic", "rank_in_source_response": 7, "raw_value": "0.45", "reported_by": "third_party", "reported_date": "2026-05-28", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.45, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2", "model_name": "Claude Opus 4.7 (Adaptive Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2", "organization": "Anthropic", "rank_in_source_response": 9, "raw_value": "0.4375", "reported_by": "third_party", "reported_date": "2026-04-16", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.4375, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "bbd93ebe-80da-4594-bb19-61e69d0331df", "model_name": "Gemini 3.1 Pro Preview", "obs_id": "artificial_analysis:aa-analystagent:bbd93ebe-80da-4594-bb19-61e69d0331df", "organization": "Google", "rank_in_source_response": 10, "raw_value": "0.4125", "reported_by": "third_party", "reported_date": "2026-02-19", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.4125, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "c8adc5cf-fd5a-407b-af51-dc3bede3e49c", "model_name": "Grok 4.6 (high)", "obs_id": "artificial_analysis:aa-analystagent:c8adc5cf-fd5a-407b-af51-dc3bede3e49c", "organization": "xAI", "rank_in_source_response": 10, "raw_value": "0.4125", "reported_by": "third_party", "reported_date": "2026-08-12", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.4125, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "f7d2fc3e-1f7b-405f-818c-07952a4af78f", "model_name": "Kimi K3 (max)", "obs_id": "artificial_analysis:aa-analystagent:f7d2fc3e-1f7b-405f-818c-07952a4af78f", "organization": "Moonshot AI", "rank_in_source_response": 12, "raw_value": "0.3875", "reported_by": "third_party", "reported_date": "2026-07-16", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.3875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "794f69b5-cede-482b-b1cc-d769478497cd", "model_name": "Grok 4.5 (high)", "obs_id": "artificial_analysis:aa-analystagent:794f69b5-cede-482b-b1cc-d769478497cd", "organization": "xAI", "rank_in_source_response": 13, "raw_value": "0.35", "reported_by": "third_party", "reported_date": "2026-07-08", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.35, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "7261504e-503c-4a66-a9d3-a3272cdf9ad6", "model_name": "Inkling Small", "obs_id": "artificial_analysis:aa-analystagent:7261504e-503c-4a66-a9d3-a3272cdf9ad6", "organization": "Thinking Machines", "rank_in_source_response": 14, "raw_value": "0.275", "reported_by": "third_party", "reported_date": "2026-07-30", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.275, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "d8ddb241-b3e4-4c25-a6a3-72eb1b30c541", "model_name": "DeepSeek V4 Flash (Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:d8ddb241-b3e4-4c25-a6a3-72eb1b30c541", "organization": "DeepSeek", "rank_in_source_response": 15, "raw_value": "0.25", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.25, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "0de09623-2b1a-4c8d-86ef-7f5245d4e24b", "model_name": "Inkling (xhigh)", "obs_id": "artificial_analysis:aa-analystagent:0de09623-2b1a-4c8d-86ef-7f5245d4e24b", "organization": "Thinking Machines", "rank_in_source_response": 16, "raw_value": "0.2375", "reported_by": "third_party", "reported_date": "2026-07-15", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.2375, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "00f1248e-78e3-4230-8dc8-5e13ba8645e2", "model_name": "MiMo-V2.5-Pro", "obs_id": "artificial_analysis:aa-analystagent:00f1248e-78e3-4230-8dc8-5e13ba8645e2", "organization": "Xiaomi", "rank_in_source_response": 17, "raw_value": "0.2", "reported_by": "third_party", "reported_date": "2026-04-22", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.2, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "df8d14e0-3997-4e4d-b4ad-9c047acc9c69", "model_name": "Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:df8d14e0-3997-4e4d-b4ad-9c047acc9c69", "organization": "Anthropic", "rank_in_source_response": 17, "raw_value": "0.2", "reported_by": "third_party", "reported_date": "2026-02-17", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.2, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "69534bed-2ffd-4235-832b-e20a810333ab", "model_name": "Qwen3.7 Max", "obs_id": "artificial_analysis:aa-analystagent:69534bed-2ffd-4235-832b-e20a810333ab", "organization": "Qwen", "rank_in_source_response": 19, "raw_value": "0.1875", "reported_by": "third_party", "reported_date": "2026-05-19", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.1875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "bf220674-68bd-43cc-a1b8-ce5ed4d2f18d", "model_name": "DeepSeek V4 Pro (Reasoning, Max Effort)", "obs_id": "artificial_analysis:aa-analystagent:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d", "organization": "DeepSeek", "rank_in_source_response": 19, "raw_value": "0.1875", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.1875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "a6340098-d7ae-462d-b372-0a0a67fc44b4", "model_name": "Claude 4.5 Haiku (Reasoning)", "obs_id": "artificial_analysis:aa-analystagent:a6340098-d7ae-462d-b372-0a0a67fc44b4", "organization": "Anthropic", "rank_in_source_response": 21, "raw_value": "0.15", "reported_by": "third_party", "reported_date": "2025-10-15", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.15, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "ba242e40-83b7-4cd3-a0e0-b56237984914", "model_name": "GPT-5.4 mini (xhigh)", "obs_id": "artificial_analysis:aa-analystagent:ba242e40-83b7-4cd3-a0e0-b56237984914", "organization": "OpenAI", "rank_in_source_response": 21, "raw_value": "0.15", "reported_by": "third_party", "reported_date": "2026-03-17", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.15, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "dd059b25-d82a-4ead-82a4-4adceaaec48b", "model_name": "Mistral Medium 3.5", "obs_id": "artificial_analysis:aa-analystagent:dd059b25-d82a-4ead-82a4-4adceaaec48b", "organization": "Mistral", "rank_in_source_response": 23, "raw_value": "0.125", "reported_by": "third_party", "reported_date": "2026-04-29", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.125, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "4bbceacb-cf47-464b-b60f-e1d1fe016d67", "model_name": "MiniMax-M2.7", "obs_id": "artificial_analysis:aa-analystagent:4bbceacb-cf47-464b-b60f-e1d1fe016d67", "organization": "MiniMax", "rank_in_source_response": 24, "raw_value": "0.1125", "reported_by": "third_party", "reported_date": "2026-03-18", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.1125, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "277f939a-985b-4b37-859d-b3eabc7c0b26", "model_name": "MiniMax-M3", "obs_id": "artificial_analysis:aa-analystagent:277f939a-985b-4b37-859d-b3eabc7c0b26", "organization": "MiniMax", "rank_in_source_response": 25, "raw_value": "0.1", "reported_by": "third_party", "reported_date": "2026-06-01", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.1, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "598190f8-dc9c-4fea-a7ea-4b81c402ab18", "model_name": "Gemini 3.1 Flash-Lite", "obs_id": "artificial_analysis:aa-analystagent:598190f8-dc9c-4fea-a7ea-4b81c402ab18", "organization": "Google", "rank_in_source_response": 26, "raw_value": "0.0875", "reported_by": "third_party", "reported_date": "2026-03-03", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.0875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "948892b5-db03-4118-a4a8-ccd51ed871ea", "model_name": "Grok 4.3 (high)", "obs_id": "artificial_analysis:aa-analystagent:948892b5-db03-4118-a4a8-ccd51ed871ea", "organization": "xAI", "rank_in_source_response": 26, "raw_value": "0.0875", "reported_by": "third_party", "reported_date": "2026-04-30", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.0875, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "6f1a7562-6e96-46ac-af4f-6ba5a7a3da96", "model_name": "GPT-5.5 (Non-reasoning)", "obs_id": "artificial_analysis:aa-analystagent:6f1a7562-6e96-46ac-af4f-6ba5a7a3da96", "organization": "OpenAI", "rank_in_source_response": 28, "raw_value": "0.075", "reported_by": "third_party", "reported_date": "2026-04-23", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.075, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "5b52def2-ac9b-4465-ad80-91ea8079e253", "model_name": "Nemotron 3 Ultra 550B A55B (Reasoning)", "obs_id": "artificial_analysis:aa-analystagent:5b52def2-ac9b-4465-ad80-91ea8079e253", "organization": "NVIDIA", "rank_in_source_response": 29, "raw_value": "0.0625", "reported_by": "third_party", "reported_date": "2026-06-04", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.0625, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-25T10:41:06Z", "date_precision": "model_announcement", "document_id": "artificial_analysis:https://artificialanalysis.ai/evaluations/aa-analyst-agent", "key": "artificial-analysis:aa-analystagent", "measured_by": "Artificial Analysis", "model_id": "3fd96175-4ef1-434c-8795-f873aec2abc1", "model_name": "Mistral Small 4 (Reasoning)", "obs_id": "artificial_analysis:aa-analystagent:3fd96175-4ef1-434c-8795-f873aec2abc1", "organization": "Mistral", "rank_in_source_response": 30, "raw_value": "0.0125", "reported_by": "third_party", "reported_date": "2026-03-16", "series_id": "artificial_analysis:aa-analystagent:default", "source": "artificial_analysis", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent", "value": 0.0125, "value_kind": "number"}], "series": {"bounds": {"basis": "aggregator_declared", "max": null, "min": null}, "declared_max": null, "direction": "higher_is_better", "direction_basis": "source_rank_descending", "display_scale": null, "first_score_record": {"date_precision": "model_announcement", "obs_id": "artificial_analysis:aa-analystagent:a6340098-d7ae-462d-b372-0a0a67fc44b4", "reported_at": "2025-10-15", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent"}, "first_score_report": null, "key": "artificial-analysis:aa-analystagent", "max_score_contradicted": false, "metric": null, "observation_count": 30, "observed_max": 0.6, "score_summary": {"display_max": 60.0, "display_multiplier": 100, "model_count": 30, "model_count_basis": "source_model_id", "numeric_count": 30, "raw_max": 0.6, "raw_min": 0.0125, "source_reference": {"crawled_at": "2026-08-25T10:41:06Z", "obs_id": "artificial_analysis:aa-analystagent:b2331108-72ed-415a-82d1-188633875bbc", "reported_date": "2026-08-13", "source_url": "https://artificialanalysis.ai/evaluations/aa-analyst-agent"}, "unit": null}, "series_id": "artificial_analysis:aa-analystagent:default"}}}, "siblings": []}
