{"observation":{"id":"4f68e405-a4c7-4191-b4bc-3c3a430b14b4","tool":"upstage-ai","tool_name":"Upstage AI","criterion":"complex-document-handling","criterion_name":"Complex Document Handling","criterion_definition":"Maintains quality across long, multi-section, and mixed-content documents without degradation.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"The subject explicitly says complex PDF, so sustained quality across long, mixed-content documents is central to the tool’s ability to do the job. (3 of 3 judges)","scenario":"hybrid-earnings-report","scenario_name":"Hybrid Earnings Report","group_tag":"hybrid-earnings-report","scenario_description":"A long, real-world hybrid annual report used to benchmark end-to-end PDF-to-markdown conversion. It combines native text, financial tables, charts/graphics, and scanned signature/stamp regions, stressing preservation of document structure, reading order, and embedded visual content across a multi-section report.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://cdn.futuresmart.ai/public/aidemos/f63a44b441704753b65d1b89dc9b4bbb.pdf?v=1","role":"input","filename":"Target-2015-Annual-Report.pdf"}],"stresses":["Native digital text extraction","Complex financial table preservation","Chart and graphic retention","Image-based signatures and stamps","Reading order across a long multi-section report","Markdown quality and consistency"],"verdict":"mixed","score":null,"score_total":null,"note":"Handles an 84-page hybrid report end to end, but quality degrades on signatures and multicolumn pages rather than staying uniform across the document.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/07829e6dcb414445886e618cd047efb2.pdf?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/77b9376a08414738957b42f189340237.mp4?v=1","role":"context","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/1f45fe222ffc4719ad527014bd6fabbf.png?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/adb683c35665414898107043d7650bc0.png?v=1","role":"input","alt":null}],"run_id":"6e3160de-fe46-4b45-b071-72560b5c5d0e","study_title":"Convert a Complex PDF into Clean Markdown with an API","study_kind":"generation","research_task":"86b9h7t37","tested_at":null,"completeness":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://cdn.futuresmart.ai/public/aidemos/f63a44b441704753b65d1b89dc9b4bbb.pdf?v=1","filename":"Target-2015-Annual-Report.pdf","alt":"Hybrid Earnings Report","role":"input"}],"modality":"pdf","stresses":["Native digital text extraction","Complex financial table preservation","Chart and graphic retention","Image-based signatures and stamps","Reading order across a long multi-section report","Markdown quality and consistency"]},"tool_page_slug":"upstage-ai","tool_url":"https://aidemos.com/tools/upstage-ai","permalink":"https://aidemos.com/evidence/4f68e405-a4c7-4191-b4bc-3c3a430b14b4","api_url":"https://ai.aidemos.com/v1/observations/4f68e405-a4c7-4191-b4bc-3c3a430b14b4"},"peers":[{"id":"b6400536-c5b3-4232-860e-82a4570ba4fb","tool":"adobe-api","tool_name":"Adobe API","verdict":"worked","score":null,"score_total":null,"note":"Processes a long mixed-content annual report in one automated run, keeping tables, charts, and scanned signature pages in the extracted output.","artifact_count":6,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/07829e6dcb414445886e618cd047efb2.pdf?v=1","evidence_url":"https://aidemos.com/evidence/b6400536-c5b3-4232-860e-82a4570ba4fb"},{"id":"6cfee092-61f2-4247-aaff-49291fa4a600","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Processes an 84-page hybrid annual report end-to-end across native text, tables, charts, and scan-only signature regions without manual cleanup.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/07829e6dcb414445886e618cd047efb2.pdf?v=1","evidence_url":"https://aidemos.com/evidence/6cfee092-61f2-4247-aaff-49291fa4a600"},{"id":"067d4ba1-ae97-4111-b551-af220e9d5046","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Handles an 84-page mixed-content annual report end-to-end and reaches SUCCESS in the Results view without manual correction.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/df693717929743e88e88420c4dca7ef2.mp4?v=1","evidence_url":"https://aidemos.com/evidence/067d4ba1-ae97-4111-b551-af220e9d5046"},{"id":"8217f0a1-861e-4d16-9d7a-f644f646e9c2","tool":"mistral-ai","tool_name":"Mistral AI","verdict":"worked","score":null,"score_total":null,"note":"The tool handles an 84-page mixed-content annual report end-to-end, including tables, charts, and scanned signature/stamp regions, and returns usable markdown output without manual correction.","artifact_count":5,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/5b75fe2928234e9eb83c5d154f00d4eb.mp4?v=1","evidence_url":"https://aidemos.com/evidence/8217f0a1-861e-4d16-9d7a-f644f646e9c2"},{"id":"b8766f4f-a4c2-4305-a922-cf1617bc9713","tool":"nutrient-io","tool_name":"Nutrient.io","verdict":"worked","score":null,"score_total":null,"note":"Handles an 84-page mixed-content annual report end to end, including native text, tables, charts, and scanned signature pages, and returns a markdown export.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/07829e6dcb414445886e618cd047efb2.pdf?v=1","evidence_url":"https://aidemos.com/evidence/b8766f4f-a4c2-4305-a922-cf1617bc9713"},{"id":"cc063370-eea8-45f8-aabb-b5ba6830abae","tool":"pdfvector","tool_name":"PDFVector","verdict":"worked","score":null,"score_total":null,"note":"Handled an 84-page hybrid annual report without errors.","artifact_count":4,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/07829e6dcb414445886e618cd047efb2.pdf?v=1","evidence_url":"https://aidemos.com/evidence/cc063370-eea8-45f8-aabb-b5ba6830abae"},{"id":"1961fa7a-2d5a-4ece-83fe-23b4c0399568","tool":"reducto","tool_name":"Reducto","verdict":"mixed","score":null,"score_total":null,"note":"Processes the full 84-page mixed-content report in 25.5 seconds with no truncation and keeps the hardest nested table’s 27 values exact, but 10 footer numbers are corrupted in the back two-thirds of the file.","artifact_count":9,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-reducto-input1-hybridearnings-output-2e5bed5d1e5a.md","evidence_url":"https://aidemos.com/evidence/1961fa7a-2d5a-4ece-83fe-23b4c0399568"},{"id":"b119f634-824d-42b8-8ece-5462ea6b4f0c","tool":"tensorlake","tool_name":"Tensorlake","verdict":"worked","score":null,"score_total":null,"note":"Processes an 84-page mixed-content annual report without collapsing the hierarchy, keeping text, tables, charts, and scanned signatures usable within the extracted workflow.","artifact_count":7,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/b5fe76bd1e0a4c67a7f552a313dd5116.png?v=1","evidence_url":"https://aidemos.com/evidence/b119f634-824d-42b8-8ece-5462ea6b4f0c"}],"other_criteria":[{"id":"e260a099-6895-499f-ab5d-82e11a0cf513","criterion":"advanced-features","criterion_name":"Advanced Features","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"Separately extracts chart content into textual summaries and value tables, including a waterfall chart and bar charts with year/value pairs and growth statistics.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/e260a099-6895-499f-ab5d-82e11a0cf513"},{"id":"07e93c54-d160-40c0-b3ba-519704752930","criterion":"reading-order-structure","criterion_name":"Reading Order & Structure","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Breaks the two-column reading order on the annual-report page, so headings and body text no longer follow the source navigation cleanly.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/07e93c54-d160-40c0-b3ba-519704752930"},{"id":"eadd62f1-5229-47c5-9d69-024cbf87e51b","criterion":"table-preservation","criterion_name":"Table Preservation","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Reconstructs the 2011–2015 financial summary table with rows and columns intact, but misses a small number of currency symbols in the extracted values.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/eadd62f1-5229-47c5-9d69-024cbf87e51b"},{"id":"417a2325-3f7b-4e6f-a06f-e7653967e43e","criterion":"visual-content-retention","criterion_name":"Visual Content Retention","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Does not retain handwritten signature content as visual output on the signatures page, leaving only partial surrounding legal text and no clearly identifiable signatures.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/417a2325-3f7b-4e6f-a06f-e7653967e43e"}],"appears_in":[{"page_type":"ranking","slug":"pdf-to-markdown-apis","title":"Best AI Tools to Convert Complex PDFs into Clean Markdown with an API","url":"https://aidemos.com/best/pdf-to-markdown-apis","binding":"run"}],"same_scenario":[{"id":"b6400536-c5b3-4232-860e-82a4570ba4fb","tool":"adobe-api","tool_name":"Adobe API","verdict":"worked","score":null,"score_total":null,"note":"Processes a long mixed-content annual report in one automated run, keeping tables, charts, and scanned signature pages in the extracted output."},{"id":"6cfee092-61f2-4247-aaff-49291fa4a600","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Processes an 84-page hybrid annual report end-to-end across native text, tables, charts, and scan-only signature regions without manual cleanup."},{"id":"067d4ba1-ae97-4111-b551-af220e9d5046","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Handles an 84-page mixed-content annual report end-to-end and reaches SUCCESS in the Results view without manual correction."},{"id":"8217f0a1-861e-4d16-9d7a-f644f646e9c2","tool":"mistral-ai","tool_name":"Mistral AI","verdict":"worked","score":null,"score_total":null,"note":"The tool handles an 84-page mixed-content annual report end-to-end, including tables, charts, and scanned signature/stamp regions, and returns usable markdown output without manual correction."},{"id":"b8766f4f-a4c2-4305-a922-cf1617bc9713","tool":"nutrient-io","tool_name":"Nutrient.io","verdict":"worked","score":null,"score_total":null,"note":"Handles an 84-page mixed-content annual report end to end, including native text, tables, charts, and scanned signature pages, and returns a markdown export."},{"id":"cc063370-eea8-45f8-aabb-b5ba6830abae","tool":"pdfvector","tool_name":"PDFVector","verdict":"worked","score":null,"score_total":null,"note":"Handled an 84-page hybrid annual report without errors."},{"id":"1961fa7a-2d5a-4ece-83fe-23b4c0399568","tool":"reducto","tool_name":"Reducto","verdict":"mixed","score":null,"score_total":null,"note":"Processes the full 84-page mixed-content report in 25.5 seconds with no truncation and keeps the hardest nested table’s 27 values exact, but 10 footer numbers are corrupted in the back two-thirds of the file."},{"id":"b119f634-824d-42b8-8ece-5462ea6b4f0c","tool":"tensorlake","tool_name":"Tensorlake","verdict":"worked","score":null,"score_total":null,"note":"Processes an 84-page mixed-content annual report without collapsing the hierarchy, keeping text, tables, charts, and scanned signatures usable within the extracted workflow."}]}