Graded 4 October 2026
Can Upstage AI preserve a data chart and its title when converting a document to Markdown?
Upstage AI failed this PDF-chart scenario: the page-3 chart was not preserved as an image with its title. The Markdown shows a placeholder image, 'Chart Type: bar', and a wrong value table; the surrounding prose and page-2 Figure 1 caption remain.
1 of 1 test case failed
Every test case in this scenario has a result.
Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
Data chart — preserved with titleFailEvidence
What we sent
InputDocument (PDF)
What the tool returned
The tool returned 2 files.
Output file (Markdown)
Markdown107 lines
# Intertidal survey of Kellow Sands and Thrimby Point Report BEP/SR/2026/11 · Survey of 19 to 23 January 2026 · Issued February 2026 # Summary The four fixed transects at Kellow Sands and Thrimby Point were resurveyed in January, in the third winter since sediment recharge began. This report sets out the method, the profiles measured, and the change on each transect since the surveys began. Levels were taken at five-metre intervals along each transect with a total station from the survey marks on the training wall and at the lifeboat house. Sediment samples were taken at the mid-shore station on each transect for particle size, and are reported by the laboratory separately. Conditions during the survey were settled, with no swell and a spring range near the mean. Nothing about the week's weather is likely to have affected the levels measured. # Background The Partnership has surveyed the intertidal at Kellow Sands since 2019, when the four transects were established to provide a baseline for the sediment recharge then being planned. The first two winters were surveyed before any material was placed. Placement began in the winter of 2023/24 and has been carried out in each winter since, most recently between November 2025 and January 2026. The purpose of the survey is a narrow one. It is meant to answer whether the intertidal profile at Kellow Sands is gaining or losing sediment, and at what rate, on lines whose position is fixed. It is not a study of where the placed material goes, which would need tracer work the Partnership has not commissioned, and it cannot by itself attribute a change to the recharge rather than to the weather. # Method Levels were taken with a total station from the two survey marks used since 2019, at five-metre intervals along each transect and at every break of slope between them. Each line was run twice, out and back, and the two sets agreed everywhere within the tolerance the method allows. Where they did not, which happened once on transect three, the point was re-observed. The horizontal position of each line is fixed by a mark set in concrete at the landward end and by a pin in the training wall or the marsh edge at the seaward end. All eight marks were found and checked against the 2019 coordinates before work began. The pin at the seaward end of transect two has moved and was re-established from the landward mark; the correction is recorded in the level book and is smaller than the interval between observations. Sediment samples were taken at the mid-shore station on each line, in the order in which the lines were surveyed, and delivered to the laboratory the same afternoon. Particle size is reported separately and is not discussed here. The transects Transect one runs from the seawall opposite the boatyard to the low water mark, crossing the widest part of the sand. It is the longest of the four lines and the only one on which the whole intertidal profile can be surveyed within a single tide. Transects two and three are the pair the recharge was expected to affect. Both cross the placement footprint at its northern end, transect two some sixty metres from the discharge point and transect three about a hundred and forty. Neither has been moved since it was established, and the marks at both ends of both lines were found in good order. The plan below shows the four lines as they were surveyed in January, together with the saltmarsh edge as it stood at the 1998 survey. The 1998 edge is drawn because it is the last edge surveyed on the ground rather than taken from photography, and because it is the line against which the advisers have asked that marsh extent be reported.  T1 N Kellow Sands T2 Thrimby Point T3 T4 Figure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh edge as a broken line. Transect four crosses the toe of the training wall and has always behaved differently from the other three. It is retained because the wall itself is the reason for the difference, and because the Partnership was asked in 2019 to keep a line there. The stations shown on the plan are those at which sediment samples are taken, and not the points at which levels were observed: the level observations are too close together to plot at this scale. A full set of profiles is bound into the copy of this report held by the secretariat. Change since the first survey Change is reported as a mean annual rate over each winter, taken across the whole intertidal part of the line. Accretion varied markedly between transects, and the pattern is the same in each of the three winters measured.  - Chart Type: bar | | Transect 1 | Transect 2 | Transect 3 | Transect 4 | | --- | --- | --- | --- | --- | | 2023/24 | 0.5mm/yr | 2.7mm/yr | 2.9mm/yr | -0.2mm/yr | | 2024/25 | 0.3mm/yr | 3.8mm/yr | 2.7mm/yr | -0.2mm/yr | | 2025/26 | 0.8mm/yr | 3.9mm/yr | 0.3mm/yr | -0.2mm/yr | The rates plotted are means over the intertidal part of each line, weighted by the length of profile each observation represents. A mean of that kind conceals a good deal. On transect two most of the gain is in the upper third of the profile, and on transect four the loss is almost all at the toe of the wall; the profiles show this plainly and a mean does not. The advisers' view, which the secretariat shares, is that three winters is too short a run to separate the effect of placement from the variation the estuary shows anyway. The transects should be resurveyed next January on the same lines and by the same method before anything is concluded from them. The next survey The profiles themselves, the level books and the mark check sheets are held by the secretariat and are available to Partnership members on request. The next survey is due in January 2027. The secretariat proposes to keep the January window, and to ask the laboratory for particle size on the same four stations so that the series stays comparable.
Output file (JSON)
Cited values1 value from this file
- elements 24 › content › html
- <figure id='23' data-category='chart'><img data-coord="top-left:(130,342); bottom-right:(1111,929)" /><figcaption><p>Chart Type: bar</p></figcaption><table><thead><tr><td></td><td>Transect 1</td><td>Transect 2</td><td>Transect 3</td><td>Transect 4</td></tr></thead><tbody><tr><td>2023/24</td><td>0.5mm/yr</td><td>2.7mm/yr</td><td>2.9mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2024/25</td><td>0.3mm/yr</td><td>3.8mm/yr</td><td>2.7mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2025/26</td><td>0.8mm/yr</td><td>3.9mm/yr</td><td>0.3mm/yr</td><td>-0.2mm/yr</td></tr></tbody></table></figure>
Show the whole file (41 KB)
JSON
{ "api": "2.0", "content": { "html": "<h1 id='0' style='font-size:20px'>Intertidal survey of Kellow Sands and Thrimby Point</h1>\n<p id='1' data-category='paragraph' style='font-size:14px'>Report BEP/SR/2026/11 \u00b7 Survey of 19 to 23 January 2026 \u00b7 Issued February 2026</p>\n<h1 id='2' style='font-size:16px'>Summary</h1>\n<p id='3' data-category='paragraph' style='font-size:14px'>The four fixed transects at Kellow Sands and Thrimby Point were resurveyed in January, in the third winter<br>since sediment recharge began. This report sets out the method, the profiles measured, and the change on<br>each transect since the surveys began.</p>\n<p id='4' data-category='paragraph' style='font-size:14px'>Levels were taken at five-metre intervals along each transect with a total station from the survey marks on<br>the training wall and at the lifeboat house. Sediment samples were taken at the mid-shore station on each<br>transect for particle size, and are reported by the laboratory separately.</p>\n<p id='5' data-category='paragraph' style='font-size:14px'>Conditions during the survey were settled, with no swell and a spring range near the mean. Nothing about<br>the week's weather is likely to have affected the levels measured.</p>\n<h1 id='6' style='font-size:16px'>Background</h1>\n<p id='7' data-category='paragraph' style='font-size:14px'>The Partnership has surveyed the intertidal at Kellow Sands since 2019, when the four transects were<br>established to provide a baseline for the sediment recharge then being planned. The first two winters were<br>surveyed before any material was placed. Placement began in the winter of 2023/24 and has been carried<br>out in each winter since, most recently between November 2025 and January 2026.</p>\n<p id='8' data-category='paragraph' style='font-size:14px'>The purpose of the survey is a narrow one. It is meant to answer whether the intertidal profile at Kellow<br>Sands is gaining or losing sediment, and at what rate, on lines whose position is fixed. It is not a study of<br>where the placed material goes, which would need tracer work the Partnership has not commissioned, and<br>it cannot by itself attribute a change to the recharge rather than to the weather.</p>\n<h1 id='9' style='font-size:16px'>Method</h1>\n<p id='10' data-category='paragraph' style='font-size:14px'>Levels were taken with a total station from the two survey marks used since 2019, at five-metre intervals<br>along each transect and at every break of slope between them. Each line was run twice, out and back, and<br>the two sets agreed everywhere within the tolerance the method allows. Where they did not, which<br>happened once on transect three, the point was re-observed.</p>\n<p id='11' data-category='paragraph' style='font-size:14px'>The horizontal position of each line is fixed by a mark set in concrete at the landward end and by a pin in the<br>training wall or the marsh edge at the seaward end. All eight marks were found and checked against the<br>2019 coordinates before work began. The pin at the seaward end of transect two has moved and was<br>re-established from the landward mark; the correction is recorded in the level book and is smaller than the<br>interval between observations.</p>\n<p id='12' data-category='paragraph' style='font-size:14px'>Sediment samples were taken at the mid-shore station on each line, in the order in which the lines were<br>surveyed, and delivered to the laboratory the same afternoon. Particle size is reported separately and is not<br>discussed here.</p>\n<p id='13' data-category='paragraph' style='font-size:20px'>The transects</p>\n<p id='14' data-category='paragraph' style='font-size:18px'>Transect one runs from the seawall opposite the boatyard to the low water mark, crossing the widest part of<br>the sand. It is the longest of the four lines and the only one on which the whole intertidal profile can be<br>surveyed within a single tide.</p>\n<p id='15' data-category='paragraph' style='font-size:18px'>Transects two and three are the pair the recharge was expected to affect. Both cross the placement<br>footprint at its northern end, transect two some sixty metres from the discharge point and transect three<br>about a hundred and forty. Neither has been moved since it was established, and the marks at both ends of<br>both lines were found in good order.</p>\n<p id='16' data-category='paragraph' style='font-size:18px'>The plan below shows the four lines as they were surveyed in January, together with the saltmarsh edge as<br>it stood at the 1998 survey. The 1998 edge is drawn because it is the last edge surveyed on the ground<br>rather than taken from photography, and because it is the line against which the advisers have asked that<br>marsh extent be reported.</p>\n<figure id='17'><img style='font-size:14px' alt=\"T1 N Kellow Sands T2 Thrimby Point T3 T4\" data-coord=\"top-left:(222,599); bottom-right:(1017,988)\" /></figure>\n<p id='18' data-category='caption' style='font-size:16px'>Figure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh<br>edge as a broken line.</p>\n<p id='19' data-category='paragraph' style='font-size:18px'>Transect four crosses the toe of the training wall and has always behaved differently from the other three. It<br>is retained because the wall itself is the reason for the difference, and because the Partnership was asked<br>in 2019 to keep a line there.</p>\n<p id='20' data-category='paragraph' style='font-size:18px'>The stations shown on the plan are those at which sediment samples are taken, and not the points at which<br>levels were observed: the level observations are too close together to plot at this scale. A full set of profiles<br>is bound into the copy of this report held by the secretariat.</p>\n<p id='21' data-category='paragraph' style='font-size:18px'>Change since the first survey</p>\n<p id='22' data-category='paragraph' style='font-size:14px'>Change is reported as a mean annual rate over each winter, taken across the whole intertidal part of the<br>line. Accretion varied markedly between transects, and the pattern is the same in each of the three winters<br>measured.</p>\n<figure id='23' data-category='chart'><img data-coord=\"top-left:(130,342); bottom-right:(1111,929)\" /><figcaption><p>Chart Type: bar</p></figcaption><table><thead><tr><td></td><td>Transect 1</td><td>Transect 2</td><td>Transect 3</td><td>Transect 4</td></tr></thead><tbody><tr><td>2023/24</td><td>0.5mm/yr</td><td>2.7mm/yr</td><td>2.9mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2024/25</td><td>0.3mm/yr</td><td>3.8mm/yr</td><td>2.7mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2025/26</td><td>0.8mm/yr</td><td>3.9mm/yr</td><td>0.3mm/yr</td><td>-0.2mm/yr</td></tr></tbody></table></figure>\n<p id='24' data-category='paragraph' style='font-size:14px'>The rates plotted are means over the intertidal part of each line, weighted by the length of profile each<br>observation represents. A mean of that kind conceals a good deal. On transect two most of the gain is in the<br>upper third of the profile, and on transect four the loss is almost all at the toe of the wall; the profiles show<br>this plainly and a mean does not.</p>\n<p id='25' data-category='paragraph' style='font-size:14px'>The advisers' view, which the secretariat shares, is that three winters is too short a run to separate the<br>effect of placement from the variation the estuary shows anyway. The transects should be resurveyed next<br>January on the same lines and by the same method before anything is concluded from them.</p>\n<p id='26' data-category='paragraph' style='font-size:18px'>The next survey</p>\n<p id='27' data-category='paragraph' style='font-size:14px'>The profiles themselves, the level books and the mark check sheets are held by the secretariat and are<br>available to Partnership members on request.</p>\n<p id='28' data-category='paragraph' style='font-size:14px'>The next survey is due in January 2027. The secretariat proposes to keep the January window, and to ask<br>the laboratory for particle size on the same four stations so that the series stays comparable.</p>", "markdown": "# Intertidal survey of Kellow Sands and Thrimby Point\n\nReport BEP/SR/2026/11 \u00b7 Survey of 19 to 23 January 2026 \u00b7 Issued February 2026\n\n# Summary\n\nThe four fixed transects at Kellow Sands and Thrimby Point were resurveyed in January, in the third winter\nsince sediment recharge began. This report sets out the method, the profiles measured, and the change on\neach transect since the surveys began.\n\nLevels were taken at five-metre intervals along each transect with a total station from the survey marks on\nthe training wall and at the lifeboat house. Sediment samples were taken at the mid-shore station on each\ntransect for particle size, and are reported by the laboratory separately.\n\nConditions during the survey were settled, with no swell and a spring range near the mean. Nothing about\nthe week's weather is likely to have affected the levels measured.\n\n# Background\n\nThe Partnership has surveyed the intertidal at Kellow Sands since 2019, when the four transects were\nestablished to provide a baseline for the sediment recharge then being planned. The first two winters were\nsurveyed before any material was placed. Placement began in the winter of 2023/24 and has been carried\nout in each winter since, most recently between November 2025 and January 2026.\n\nThe purpose of the survey is a narrow one. It is meant to answer whether the intertidal profile at Kellow\nSands is gaining or losing sediment, and at what rate, on lines whose position is fixed. It is not a study of\nwhere the placed material goes, which would need tracer work the Partnership has not commissioned, and\nit cannot by itself attribute a change to the recharge rather than to the weather.\n\n# Method\n\nLevels were taken with a total station from the two survey marks used since 2019, at five-metre intervals\nalong each transect and at every break of slope between them. Each line was run twice, out and back, and\nthe two sets agreed everywhere within the tolerance the method allows. Where they did not, which\nhappened once on transect three, the point was re-observed.\n\nThe horizontal position of each line is fixed by a mark set in concrete at the landward end and by a pin in the\ntraining wall or the marsh edge at the seaward end. All eight marks were found and checked against the\n2019 coordinates before work began. The pin at the seaward end of transect two has moved and was\nre-established from the landward mark; the correction is recorded in the level book and is smaller than the\ninterval between observations.\n\nSediment samples were taken at the mid-shore station on each line, in the order in which the lines were\nsurveyed, and delivered to the laboratory the same afternoon. Particle size is reported separately and is not\ndiscussed here.\n\nThe transects\n\nTransect one runs from the seawall opposite the boatyard to the low water mark, crossing the widest part of\nthe sand. It is the longest of the four lines and the only one on which the whole intertidal profile can be\nsurveyed within a single tide.\n\nTransects two and three are the pair the recharge was expected to affect. Both cross the placement\nfootprint at its northern end, transect two some sixty metres from the discharge point and transect three\nabout a hundred and forty. Neither has been moved since it was established, and the marks at both ends of\nboth lines were found in good order.\n\nThe plan below shows the four lines as they were surveyed in January, together with the saltmarsh edge as\nit stood at the 1998 survey. The 1998 edge is drawn because it is the last edge surveyed on the ground\nrather than taken from photography, and because it is the line against which the advisers have asked that\nmarsh extent be reported.\n\n\nT1 N Kellow Sands T2 Thrimby Point T3 T4\n\nFigure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh\nedge as a broken line.\n\nTransect four crosses the toe of the training wall and has always behaved differently from the other three. It\nis retained because the wall itself is the reason for the difference, and because the Partnership was asked\nin 2019 to keep a line there.\n\nThe stations shown on the plan are those at which sediment samples are taken, and not the points at which\nlevels were observed: the level observations are too close together to plot at this scale. A full set of profiles\nis bound into the copy of this report held by the secretariat.\n\nChange since the first survey\n\nChange is reported as a mean annual rate over each winter, taken across the whole intertidal part of the\nline. Accretion varied markedly between transects, and the pattern is the same in each of the three winters\nmeasured.\n\n\n- Chart Type: bar\n| | Transect 1 | Transect 2 | Transect 3 | Transect 4 |\n| --- | --- | --- | --- | --- |\n| 2023/24 | 0.5mm/yr | 2.7mm/yr | 2.9mm/yr | -0.2mm/yr |\n| 2024/25 | 0.3mm/yr | 3.8mm/yr | 2.7mm/yr | -0.2mm/yr |\n| 2025/26 | 0.8mm/yr | 3.9mm/yr | 0.3mm/yr | -0.2mm/yr |\n\n\nThe rates plotted are means over the intertidal part of each line, weighted by the length of profile each\nobservation represents. A mean of that kind conceals a good deal. On transect two most of the gain is in the\nupper third of the profile, and on transect four the loss is almost all at the toe of the wall; the profiles show\nthis plainly and a mean does not.\n\nThe advisers' view, which the secretariat shares, is that three winters is too short a run to separate the\neffect of placement from the variation the estuary shows anyway. The transects should be resurveyed next\nJanuary on the same lines and by the same method before anything is concluded from them.\n\nThe next survey\n\nThe profiles themselves, the level books and the mark check sheets are held by the secretariat and are\navailable to Partnership members on request.\n\nThe next survey is due in January 2027. The secretariat proposes to keep the January window, and to ask\nthe laboratory for particle size on the same four stations so that the series stays comparable.", "text": "" }, "elements": [ { "id": 0, "page": 1, "category": "heading1", "content": { "html": "<h1 id='0' style='font-size:20px'>Intertidal survey of Kellow Sands and Thrimby Point</h1>", "markdown": "# Intertidal survey of Kellow Sands and Thrimby Point", "text": "" }, "coordinates": [ { "x": 0.0969, "y": 0.0603 }, { "x": 0.6865, "y": 0.0603 }, { "x": 0.6865, "y": 0.08 }, { "x": 0.0969, "y": 0.08 } ] }, { "id": 1, "page": 1, "category": "paragraph", "content": { "html": "<p id='1' data-category='paragraph' style='font-size:14px'>Report BEP/SR/2026/11 \u00b7 Survey of 19 to 23 January 2026 \u00b7 Issued February 2026</p>", "markdown": "Report BEP/SR/2026/11 \u00b7 Survey of 19 to 23 January 2026 \u00b7 Issued February 2026", "text": "" }, "coordinates": [ { "x": 0.0974, "y": 0.0922 }, { "x": 0.7194, "y": 0.0922 }, { "x": 0.7194, "y": 0.1078 }, { "x": 0.0974, "y": 0.1078 } ] }, { "id": 2, "page": 1, "category": "heading1", "content": { "html": "<h1 id='2' style='font-size:16px'>Summary</h1>", "markdown": "# Summary", "text": "" }, "coordinates": [ { "x": 0.0975, "y": 0.1532 }, { "x": 0.1953, "y": 0.1532 }, { "x": 0.1953, "y": 0.1709 }, { "x": 0.0975, "y": 0.1709 } ] }, { "id": 3, "page": 1, "category": "paragraph", "content": { "html": "<p id='3' data-category='paragraph' style='font-size:14px'>The four fixed transects at Kellow Sands and Thrimby Point were resurveyed in January, in the third winter<br>since sediment recharge began. This report sets out the method, the profiles measured, and the change on<br>each transect since the surveys began.</p>", "markdown": "The four fixed transects at Kellow Sands and Thrimby Point were resurveyed in January, in the third winter\nsince sediment recharge began. This report sets out the method, the profiles measured, and the change on\neach transect since the surveys began.", "text": "" }, "coordinates": [ { "x": 0.0973, "y": 0.1851 }, { "x": 0.9021, "y": 0.1851 }, { "x": 0.9021, "y": 0.234 }, { "x": 0.0973, "y": 0.234 } ] }, { "id": 4, "page": 1, "category": "paragraph", "content": { "html": "<p id='4' data-category='paragraph' style='font-size:14px'>Levels were taken at five-metre intervals along each transect with a total station from the survey marks on<br>the training wall and at the lifeboat house. Sediment samples were taken at the mid-shore station on each<br>transect for particle size, and are reported by the laboratory separately.</p>", "markdown": "Levels were taken at five-metre intervals along each transect with a total station from the survey marks on\nthe training wall and at the lifeboat house. Sediment samples were taken at the mid-shore station on each\ntransect for particle size, and are reported by the laboratory separately.", "text": "" }, "coordinates": [ { "x": 0.0973, "y": 0.2473 }, { "x": 0.9015, "y": 0.2473 }, { "x": 0.9015, "y": 0.2964 }, { "x": 0.0973, "y": 0.2964 } ] }, { "id": 5, "page": 1, "category": "paragraph", "content": { "html": "<p id='5' data-category='paragraph' style='font-size:14px'>Conditions during the survey were settled, with no swell and a spring range near the mean. Nothing about<br>the week's weather is likely to have affected the levels measured.</p>", "markdown": "Conditions during the survey were settled, with no swell and a spring range near the mean. Nothing about\nthe week's weather is likely to have affected the levels measured.", "text": "" }, "coordinates": [ { "x": 0.0975, "y": 0.3091 }, { "x": 0.9015, "y": 0.3091 }, { "x": 0.9015, "y": 0.341 }, { "x": 0.0975, "y": 0.341 } ] }, { "id": 6, "page": 1, "category": "heading1", "content": { "html": "<h1 id='6' style='font-size:16px'>Background</h1>", "markdown": "# Background", "text": "" }, "coordinates": [ { "x": 0.098, "y": 0.3816 }, { "x": 0.221, "y": 0.3816 }, { "x": 0.221, "y": 0.3994 }, { "x": 0.098, "y": 0.3994 } ] }, { "id": 7, "page": 1, "category": "paragraph", "content": { "html": "<p id='7' data-category='paragraph' style='font-size:14px'>The Partnership has surveyed the intertidal at Kellow Sands since 2019, when the four transects were<br>established to provide a baseline for the sediment recharge then being planned. The first two winters were<br>surveyed before any material was placed. Placement began in the winter of 2023/24 and has been carried<br>out in each winter since, most recently between November 2025 and January 2026.</p>", "markdown": "The Partnership has surveyed the intertidal at Kellow Sands since 2019, when the four transects were\nestablished to provide a baseline for the sediment recharge then being planned. The first two winters were\nsurveyed before any material was placed. Placement began in the winter of 2023/24 and has been carried\nout in each winter since, most recently between November 2025 and January 2026.", "text": "" }, "coordinates": [ { "x": 0.0973, "y": 0.4141 }, { "x": 0.902, "y": 0.4141 }, { "x": 0.902, "y": 0.4795 }, { "x": 0.0973, "y": 0.4795 } ] }, { "id": 8, "page": 1, "category": "paragraph", "content": { "html": "<p id='8' data-category='paragraph' style='font-size:14px'>The purpose of the survey is a narrow one. It is meant to answer whether the intertidal profile at Kellow<br>Sands is gaining or losing sediment, and at what rate, on lines whose position is fixed. It is not a study of<br>where the placed material goes, which would need tracer work the Partnership has not commissioned, and<br>it cannot by itself attribute a change to the recharge rather than to the weather.</p>", "markdown": "The purpose of the survey is a narrow one. It is meant to answer whether the intertidal profile at Kellow\nSands is gaining or losing sediment, and at what rate, on lines whose position is fixed. It is not a study of\nwhere the placed material goes, which would need tracer work the Partnership has not commissioned, and\nit cannot by itself attribute a change to the recharge rather than to the weather.", "text": "" }, "coordinates": [ { "x": 0.0973, "y": 0.4924 }, { "x": 0.9023, "y": 0.4924 }, { "x": 0.9023, "y": 0.5587 }, { "x": 0.0973, "y": 0.5587 } ] }, { "id": 9, "page": 1, "category": "heading1", "content": { "html": "<h1 id='9' style='font-size:16px'>Method</h1>", "markdown": "# Method", "text": "" }, "coordinates": [ { "x": 0.0978, "y": 0.599 }, { "x": 0.1752, "y": 0.599 }, { "x": 0.1752, "y": 0.6149 }, { "x": 0.0978, "y": 0.6149 } ] }, { "id": 10, "page": 1, "category": "paragraph", "content": { "html": "<p id='10' data-category='paragraph' style='font-size:14px'>Levels were taken with a total station from the two survey marks used since 2019, at five-metre intervals<br>along each transect and at every break of slope between them. Each line was run twice, out and back, and<br>the two sets agreed everywhere within the tolerance the method allows. Where they did not, which<br>happened once on transect three, the point was re-observed.</p>", "markdown": "Levels were taken with a total station from the two survey marks used since 2019, at five-metre intervals\nalong each transect and at every break of slope between them. Each line was run twice, out and back, and\nthe two sets agreed everywhere within the tolerance the method allows. Where they did not, which\nhappened once on transect three, the point was re-observed.", "text": "" }, "coordinates": [ { "x": 0.0975, "y": 0.6312 }, { "x": 0.9021, "y": 0.6312 }, { "x": 0.9021, "y": 0.6969 }, { "x": 0.0975, "y": 0.6969 } ] }, { "id": 11, "page": 1, "category": "paragraph", "content": { "html": "<p id='11' data-category='paragraph' style='font-size:14px'>The horizontal position of each line is fixed by a mark set in concrete at the landward end and by a pin in the<br>training wall or the marsh edge at the seaward end. All eight marks were found and checked against the<br>2019 coordinates before work began. The pin at the seaward end of transect two has moved and was<br>re-established from the landward mark; the correction is recorded in the level book and is smaller than the<br>interval between observations.</p>", "markdown": "The horizontal position of each line is fixed by a mark set in concrete at the landward end and by a pin in the\ntraining wall or the marsh edge at the seaward end. All eight marks were found and checked against the\n2019 coordinates before work began. The pin at the seaward end of transect two has moved and was\nre-established from the landward mark; the correction is recorded in the level book and is smaller than the\ninterval between observations.", "text": "" }, "coordinates": [ { "x": 0.0972, "y": 0.7096 }, { "x": 0.9019, "y": 0.7096 }, { "x": 0.9019, "y": 0.791 }, { "x": 0.0972, "y": 0.791 } ] }, { "id": 12, "page": 1, "category": "paragraph", "content": { "html": "<p id='12' data-category='paragraph' style='font-size:14px'>Sediment samples were taken at the mid-shore station on each line, in the order in which the lines were<br>surveyed, and delivered to the laboratory the same afternoon. Particle size is reported separately and is not<br>discussed here.</p>", "markdown": "Sediment samples were taken at the mid-shore station on each line, in the order in which the lines were\nsurveyed, and delivered to the laboratory the same afternoon. Particle size is reported separately and is not\ndiscussed here.", "text": "" }, "coordinates": [ { "x": 0.0972, "y": 0.8052 }, { "x": 0.9021, "y": 0.8052 }, { "x": 0.9021, "y": 0.853 }, { "x": 0.0972, "y": 0.853 } ] }, { "id": 13, "page": 2, "category": "paragraph", "content": { "html": "<p id='13' data-category='paragraph' style='font-size:20px'>The transects</p>", "markdown": "The transects", "text": "" }, "coordinates": [ { "x": 0.0976, "y": 0.0594 }, { "x": 0.2345, "y": 0.0594 }, { "x": 0.2345, "y": 0.076 }, { "x": 0.0976, "y": 0.076 } ] }, { "id": 14, "page": 2, "category": "paragraph", "content": { "html": "<p id='14' data-category='paragraph' style='font-size:18px'>Transect one runs from the seawall opposite the boatyard to the low water mark, crossing the widest part of<br>the sand. It is the longest of the four lines and the only one on which the whole intertidal profile can be<br>surveyed within a single tide.</p>", "markdown": "Transect one runs from the seawall opposite the boatyard to the low water mark, crossing the widest part of\nthe sand. It is the longest of the four lines and the only one on which the whole intertidal profile can be\nsurveyed within a single tide.", "text": "" }, "coordinates": [ { "x": 0.0969, "y": 0.0922 }, { "x": 0.9026, "y": 0.0922 }, { "x": 0.9026, "y": 0.1411 }, { "x": 0.0969, "y": 0.1411 } ] }, { "id": 15, "page": 2, "category": "paragraph", "content": { "html": "<p id='15' data-category='paragraph' style='font-size:18px'>Transects two and three are the pair the recharge was expected to affect. Both cross the placement<br>footprint at its northern end, transect two some sixty metres from the discharge point and transect three<br>about a hundred and forty. Neither has been moved since it was established, and the marks at both ends of<br>both lines were found in good order.</p>", "markdown": "Transects two and three are the pair the recharge was expected to affect. Both cross the placement\nfootprint at its northern end, transect two some sixty metres from the discharge point and transect three\nabout a hundred and forty. Neither has been moved since it was established, and the marks at both ends of\nboth lines were found in good order.", "text": "" }, "coordinates": [ { "x": 0.0967, "y": 0.1536 }, { "x": 0.9026, "y": 0.1536 }, { "x": 0.9026, "y": 0.2189 }, { "x": 0.0967, "y": 0.2189 } ] }, { "id": 16, "page": 2, "category": "paragraph", "content": { "html": "<p id='16' data-category='paragraph' style='font-size:18px'>The plan below shows the four lines as they were surveyed in January, together with the saltmarsh edge as<br>it stood at the 1998 survey. The 1998 edge is drawn because it is the last edge surveyed on the ground<br>rather than taken from photography, and because it is the line against which the advisers have asked that<br>marsh extent be reported.</p>", "markdown": "The plan below shows the four lines as they were surveyed in January, together with the saltmarsh edge as\nit stood at the 1998 survey. The 1998 edge is drawn because it is the last edge surveyed on the ground\nrather than taken from photography, and because it is the line against which the advisers have asked that\nmarsh extent be reported.", "text": "" }, "coordinates": [ { "x": 0.0964, "y": 0.2315 }, { "x": 0.9027, "y": 0.2315 }, { "x": 0.9027, "y": 0.2981 }, { "x": 0.0964, "y": 0.2981 } ] }, { "id": 17, "page": 2, "category": "figure", "content": { "html": "<figure id='17'><img style='font-size:14px' alt=\"T1 N Kellow Sands T2 Thrimby Point T3 T4\" data-coord=\"top-left:(222,599); bottom-right:(1017,988)\" /></figure>", "markdown": "\nT1 N Kellow Sands T2 Thrimby Point T3 T4", "text": "" }, "coordinates": [ { "x": 0.179, "y": 0.3417 }, { "x": 0.82, "y": 0.3417 }, { "x": 0.82, "y": 0.5637 }, { "x": 0.179, "y": 0.5637 } ] }, { "id": 18, "page": 2, "category": "caption", "content": { "html": "<p id='18' data-category='caption' style='font-size:16px'>Figure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh<br>edge as a broken line.</p>", "markdown": "Figure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh\nedge as a broken line.", "text": "" }, "coordinates": [ { "x": 0.0958, "y": 0.5778 }, { "x": 0.9018, "y": 0.5778 }, { "x": 0.9018, "y": 0.6035 }, { "x": 0.0958, "y": 0.6035 } ] }, { "id": 19, "page": 2, "category": "paragraph", "content": { "html": "<p id='19' data-category='paragraph' style='font-size:18px'>Transect four crosses the toe of the training wall and has always behaved differently from the other three. It<br>is retained because the wall itself is the reason for the difference, and because the Partnership was asked<br>in 2019 to keep a line there.</p>", "markdown": "Transect four crosses the toe of the training wall and has always behaved differently from the other three. It\nis retained because the wall itself is the reason for the difference, and because the Partnership was asked\nin 2019 to keep a line there.", "text": "" }, "coordinates": [ { "x": 0.0968, "y": 0.6342 }, { "x": 0.9023, "y": 0.6342 }, { "x": 0.9023, "y": 0.6828 }, { "x": 0.0968, "y": 0.6828 } ] }, { "id": 20, "page": 2, "category": "paragraph", "content": { "html": "<p id='20' data-category='paragraph' style='font-size:18px'>The stations shown on the plan are those at which sediment samples are taken, and not the points at which<br>levels were observed: the level observations are too close together to plot at this scale. A full set of profiles<br>is bound into the copy of this report held by the secretariat.</p>", "markdown": "The stations shown on the plan are those at which sediment samples are taken, and not the points at which\nlevels were observed: the level observations are too close together to plot at this scale. A full set of profiles\nis bound into the copy of this report held by the secretariat.", "text": "" }, "coordinates": [ { "x": 0.097, "y": 0.6959 }, { "x": 0.902, "y": 0.6959 }, { "x": 0.902, "y": 0.745 }, { "x": 0.097, "y": 0.745 } ] }, { "id": 21, "page": 3, "category": "paragraph", "content": { "html": "<p id='21' data-category='paragraph' style='font-size:18px'>Change since the first survey</p>", "markdown": "Change since the first survey", "text": "" }, "coordinates": [ { "x": 0.098, "y": 0.0597 }, { "x": 0.3847, "y": 0.0597 }, { "x": 0.3847, "y": 0.0774 }, { "x": 0.098, "y": 0.0774 } ] }, { "id": 22, "page": 3, "category": "paragraph", "content": { "html": "<p id='22' data-category='paragraph' style='font-size:14px'>Change is reported as a mean annual rate over each winter, taken across the whole intertidal part of the<br>line. Accretion varied markedly between transects, and the pattern is the same in each of the three winters<br>measured.</p>", "markdown": "Change is reported as a mean annual rate over each winter, taken across the whole intertidal part of the\nline. Accretion varied markedly between transects, and the pattern is the same in each of the three winters\nmeasured.", "text": "" }, "coordinates": [ { "x": 0.0968, "y": 0.0919 }, { "x": 0.9024, "y": 0.0919 }, { "x": 0.9024, "y": 0.1407 }, { "x": 0.0968, "y": 0.1407 } ] }, { "id": 23, "page": 3, "category": "chart", "content": { "html": "<figure id='23' data-category='chart'><img data-coord=\"top-left:(130,342); bottom-right:(1111,929)\" /><figcaption><p>Chart Type: bar</p></figcaption><table><thead><tr><td></td><td>Transect 1</td><td>Transect 2</td><td>Transect 3</td><td>Transect 4</td></tr></thead><tbody><tr><td>2023/24</td><td>0.5mm/yr</td><td>2.7mm/yr</td><td>2.9mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2024/25</td><td>0.3mm/yr</td><td>3.8mm/yr</td><td>2.7mm/yr</td><td>-0.2mm/yr</td></tr><tr><td>2025/26</td><td>0.8mm/yr</td><td>3.9mm/yr</td><td>0.3mm/yr</td><td>-0.2mm/yr</td></tr></tbody></table></figure>", "markdown": "\n- Chart Type: bar\n| | Transect 1 | Transect 2 | Transect 3 | Transect 4 |\n| --- | --- | --- | --- | --- |\n| 2023/24 | 0.5mm/yr | 2.7mm/yr | 2.9mm/yr | -0.2mm/yr |\n| 2024/25 | 0.3mm/yr | 3.8mm/yr | 2.7mm/yr | -0.2mm/yr |\n| 2025/26 | 0.8mm/yr | 3.9mm/yr | 0.3mm/yr | -0.2mm/yr |\n", "text": "" }, "coordinates": [ { "x": 0.105, "y": 0.1955 }, { "x": 0.8957, "y": 0.1955 }, { "x": 0.8957, "y": 0.5298 }, { "x": 0.105, "y": 0.5298 } ] }, { "id": 24, "page": 3, "category": "paragraph", "content": { "html": "<p id='24' data-category='paragraph' style='font-size:14px'>The rates plotted are means over the intertidal part of each line, weighted by the length of profile each<br>observation represents. A mean of that kind conceals a good deal. On transect two most of the gain is in the<br>upper third of the profile, and on transect four the loss is almost all at the toe of the wall; the profiles show<br>this plainly and a mean does not.</p>", "markdown": "The rates plotted are means over the intertidal part of each line, weighted by the length of profile each\nobservation represents. A mean of that kind conceals a good deal. On transect two most of the gain is in the\nupper third of the profile, and on transect four the loss is almost all at the toe of the wall; the profiles show\nthis plainly and a mean does not.", "text": "" }, "coordinates": [ { "x": 0.0967, "y": 0.5535 }, { "x": 0.9029, "y": 0.5535 }, { "x": 0.9029, "y": 0.62 }, { "x": 0.0967, "y": 0.62 } ] }, { "id": 25, "page": 3, "category": "paragraph", "content": { "html": "<p id='25' data-category='paragraph' style='font-size:14px'>The advisers' view, which the secretariat shares, is that three winters is too short a run to separate the<br>effect of placement from the variation the estuary shows anyway. The transects should be resurveyed next<br>January on the same lines and by the same method before anything is concluded from them.</p>", "markdown": "The advisers' view, which the secretariat shares, is that three winters is too short a run to separate the\neffect of placement from the variation the estuary shows anyway. The transects should be resurveyed next\nJanuary on the same lines and by the same method before anything is concluded from them.", "text": "" }, "coordinates": [ { "x": 0.097, "y": 0.6326 }, { "x": 0.9027, "y": 0.6326 }, { "x": 0.9027, "y": 0.6822 }, { "x": 0.097, "y": 0.6822 } ] }, { "id": 26, "page": 4, "category": "paragraph", "content": { "html": "<p id='26' data-category='paragraph' style='font-size:18px'>The next survey</p>", "markdown": "The next survey", "text": "" }, "coordinates": [ { "x": 0.0977, "y": 0.0595 }, { "x": 0.2565, "y": 0.0595 }, { "x": 0.2565, "y": 0.0775 }, { "x": 0.0977, "y": 0.0775 } ] }, { "id": 27, "page": 4, "category": "paragraph", "content": { "html": "<p id='27' data-category='paragraph' style='font-size:14px'>The profiles themselves, the level books and the mark check sheets are held by the secretariat and are<br>available to Partnership members on request.</p>", "markdown": "The profiles themselves, the level books and the mark check sheets are held by the secretariat and are\navailable to Partnership members on request.", "text": "" }, "coordinates": [ { "x": 0.0969, "y": 0.0922 }, { "x": 0.9011, "y": 0.0922 }, { "x": 0.9011, "y": 0.1243 }, { "x": 0.0969, "y": 0.1243 } ] }, { "id": 28, "page": 4, "category": "paragraph", "content": { "html": "<p id='28' data-category='paragraph' style='font-size:14px'>The next survey is due in January 2027. The secretariat proposes to keep the January window, and to ask<br>the laboratory for particle size on the same four stations so that the series stays comparable.</p>", "markdown": "The next survey is due in January 2027. The secretariat proposes to keep the January window, and to ask\nthe laboratory for particle size on the same four stations so that the series stays comparable.", "text": "" }, "coordinates": [ { "x": 0.097, "y": 0.1372 }, { "x": 0.9016, "y": 0.1372 }, { "x": 0.9016, "y": 0.1702 }, { "x": 0.097, "y": 0.1702 } ] } ], "model": "document-parse-260630", "ocr": false, "usage": { "pages": 4, "standard": [1, 2, 3, 4] } }
Expected vs. Found
| ✗ | Expected: The chart stays as an image in place, with its title; any extra text data may be enrichment.Found: It was replaced by `` and `- Chart Type: bar`; the title is absent from the Markdown. |
Supporting proof
Proof 1Screenshot
Why this result
The page-3 chart was checked for an image, its title, and the values under the bars. The output shows a placeholder image, keeps only 'Chart Type: bar', and omits the title; the value table does not match the rendered chart.
Also observed in this test case
Other text kept. The output keeps the surrounding prose and the Figure 1 caption on page 2; the problem is limited to the page-3 chart.
Default chart recognition. Chart recognition is on by default here, so the substitution reflects the product's default behavior rather than a custom run setting.
Tested by Chandresh Bisht · evidence dated 9 September 2026
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
Software that produced the output
Upstage AI
Build or version
document-parse-260630 (API 2.0)
Plan or tier
free tier
Surface
API
Set up before the run
A PDF with a data chart and a title was required. The complete PDF was converted to Markdown in one default pass, with no per-tool flag tuning.
Tested
9 September 2026 · Chandresh Bisht
Connected to
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
How results are decided
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
The rules
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Converting a complex PDF into clean Markdown with a hosted API → | 12 scenarios · 13 tools |
| Capability | Figures & Charts → | |
| Scenario | A document with a data chart → | |
| Tool | Upstage AI → |
Global scenario definition → · Global capability definition → · Upstage AI product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
11 November 2026First publishedConverting a complex PDF into clean Markdown with a hosted API v1
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
This matches what I see
You run the same kind of test against your own setup and get the same behaviour.
Agree →This does not match
Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Point out an issue
Something here is wrong — a reference value, a transcription, a grade.
Report an issue →We have fixed this
Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/pdf-to-markdown-apis/results/upstage-ai/a-document-with-a-data-chart · 0 pass · 1 fail · coverage 1/1 · graded 2026-10-04
The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
Input · Document (PDF) ↗application/pdf · 301 KB
Output file (Markdown) ↗text/markdown · 6 KB
Output file (JSON) ↗application/json · 41 KB
Proof 1 · Screenshot ↗image/png · 92 KB
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.
Input · Document (PDF)75b2bcc613580942d7d3222254c0f0d084525c2c6521f55cffa629c49f64c608
Output file (Markdown)4a3c83010d4d7e6f77461a0ad15316548d8590df4f5c8a2b92ed4e7a03ce964f
Output file (JSON)f6bfeb1ca97eab419fe5c94d0c7cbb1e23691ed145fdb95e90eba20647b318f1
Proof 1 · Screenshot027d122b25de74ec5acf3cb23586fbb9350d464457922f68493fa0f9afbf8b80