questionId string | question string | question_types list | image image | docId int64 | ucsf_document_id string | ucsf_document_page_no string | answers list | data_split string | detections_overlay image | detections list | judge_verdicts list |
|---|---|---|---|---|---|---|---|---|---|---|---|
57344 | What is the dividend payout in 2012? | null | 4,720 | rnbx0223 | 193 | null | test | [
{
"bbox": [
94,
133,
817,
877
],
"label": "chart",
"sub_label": "bar chart"
},
{
"bbox": [
871,
133,
1593,
877
],
"label": "chart",
"sub_label": "bar chart"
},
{
"bbox": [
94,
893,
817,
1637
],
... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "This box contains a bar chart titled 'Total Assets'."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": ... | ||
57346 | What is the % of Employees in 2012 based on graph 'Distribution of Value-Added'? | null | 4,753 | rnbx0223 | 191 | null | test | [
{
"bbox": [
94,
585,
817,
1060
],
"label": "chart",
"sub_label": "line chart"
},
{
"bbox": [
865,
585,
1602,
1060
],
"label": "chart",
"sub_label": "line chart"
},
{
"bbox": [
94,
1106,
817,
1581
... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "Box #0 contains a line chart titled 'Gross Income'."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "... | ||
61870 | What is the personnel costs in the 4th year? | null | 8,103 | hrfw0227 | 24 | null | test | [] | [] | ||
65129 | What is the table number? | null | 10,743 | zlmg0227 | 20 | null | test | [] | [] | ||
16390 | What is the Log-in No. ? | null | 5,167 | fryn0081 | 9 | null | test | [
{
"bbox": [
170,
1859,
763,
1931
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box tightly encloses a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "... | ||
46240 | Which meeting is expected to have the highest ' attendance ' ? | null | 13,225 | ysbw0217 | 14 | null | test | [] | [] | ||
65127 | What is plotted along the x axis ? | null | 10,723 | mslw0227 | 22 | null | test | [
{
"bbox": [
152,
456,
883,
1196
],
"label": "chart",
"sub_label": ""
},
{
"bbox": [
981,
456,
1722,
1196
],
"label": "chart",
"sub_label": ""
},
{
"bbox": [
152,
1310,
883,
1993
],
"label": "c... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The box contains a scatter plot, which is a type of chart."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"rea... | ||
61883 | What is the second subheading? | null | 8,104 | jknf0227 | 6 | null | test | [] | [] | ||
61886 | Which is the railways company? | null | 8,211 | yjdv0228 | 4 | null | test | [] | [] | ||
57422 | What is the brand name of the ITC personal care product advertised here? | null | 4,783 | snbx0223 | 225 | null | test | [
{
"bbox": [
182,
851,
828,
1447
],
"label": "image",
"sub_label": "textured surface"
},
{
"bbox": [
182,
1788,
828,
2198
],
"label": "image",
"sub_label": "lab workers"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The box contains a photograph of packaged products."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason":... | ||
32850 | How many adult deaths were in 1978 as per 2nd quarter report ? | null | 9,249 | kqbf0227 | 1 | null | test | [] | [] | ||
57433 | What Tobacco brand of GPI is shown in the picture? | null | 4,809 | znbx0223 | 6 | null | test | [
{
"bbox": [
158,
779,
1724,
1573
],
"label": "image",
"sub_label": ""
},
{
"bbox": [
317,
1578,
710,
1965
],
"label": "image",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "Box #0 encloses a large photograph, which fits the definition of an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score":... | ||
16478 | What is the % Promoted Volume in EDLP stores? | null | 5,198 | hsyn0081 | 38 | null | test | [] | [] | ||
32866 | Which year was the meeting held? | null | 9,256 | jhhd0227 | 10 | null | test | [] | [] | ||
63520 | What is the full form of AHA? | null | 9,286 | hqlf0227 | 1 | null | test | [
{
"bbox": [
400,
622,
1337,
1647
],
"label": "image",
"sub_label": "illustration"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The box contains a clear illustration/drawing."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The i... | ||
49254 | Which year's Budget was this? | null | 14,275 | grvv0228 | 23 | null | test | [] | [] | ||
61895 | What is the seat number? | null | 8,207 | yjdv0228 | 13 | null | test | [
{
"bbox": [
84,
535,
312,
758
],
"label": "image",
"sub_label": ""
},
{
"bbox": [
84,
802,
312,
1025
],
"label": "image",
"sub_label": ""
},
{
"bbox": [
84,
1248,
312,
1471
],
"label": "image"... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a graphic element (a crossed-out cigarette symbol) which qualifies as an illustration/drawing."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"... | ||
32884 | What is the order no. ? | null | 9,516 | mfng0227 | 1 | null | test | [] | [] | ||
57466 | What is the name of the Centre of ITC? | null | 4,830 | snbx0223 | 226 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The image contains a photograph of an event related to the CII-ITC Centre of Excellence for Sustainable Development."
},
"LiquidAI/LFM2.5-VL-1.6B": {
... | ||
57471 | What is the title of the page? | null | 4,838 | snbx0223 | 16 | null | test | [
{
"bbox": [
128,
429,
936,
990
],
"label": "image",
"sub_label": "wheat field"
},
{
"bbox": [
255,
871,
799,
1277
],
"label": "image",
"sub_label": "group with computers"
},
{
"bbox": [
0,
1193,
1698,
... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box encloses a photograph."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The image is an embed... | ||
32895 | Which hospital is mentioned in Appendix V ? | null | 9,258 | hfyf0227 | 11 | null | test | [] | [] | ||
61905 | What is the day and date of Meeting? | null | 8,124 | jrgv0228 | 7 | null | test | [] | [] | ||
49340 | What is the name of the medical association? | null | 14,373 | nzvv0228 | 1 | null | test | [
{
"bbox": [
148,
1339,
764,
1746
],
"label": "image",
"sub_label": "map with caduceus illustration"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The bottom part of the document contains a graphic illustration, which fits the definition of an 'image'."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdic... | ||
32967 | What is the deadline date? | null | 9,287 | jpwd0227 | 1 | null | test | [
{
"bbox": [
138,
205,
274,
349
],
"label": "image",
"sub_label": "logo"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The text 'Dr. Shark' is a printed name, not a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
... | ||
57544 | What type of report is this? | null | 4,852 | snbx0223 | 224 | null | test | [
{
"bbox": [
182,
1507,
828,
2200
],
"label": "image",
"sub_label": ""
},
{
"bbox": [
867,
970,
1518,
1812
],
"label": "image",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "Box #0 contains a photograph illustrating the topic."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": ... | ||
16584 | What is the title of the document ? | null | 5,248 | kqbw0217 | 1 | null | test | [
{
"bbox": [
1014,
1783,
1418,
1912
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The handwr... | ||
40745 | What is the number of live births for Alabama? | null | 11,598 | lmyc0227 | 2 | null | test | [] | [] | ||
49353 | What is the ‘title’ of the plot? | null | 14,371 | pybv0228 | 75 | null | test | [
{
"bbox": [
472,
305,
1886,
1426
],
"label": "chart",
"sub_label": "line chart"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The image clearly contains a line graph, which falls under the category of a chart."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
... | ||
206 | What is SCGP? | null | 210 | fgfl0228 | 2 | null | test | [] | [] | ||
209 | What is written in red ink at the top? | null | 222 | yqgl0228 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The box contains printed text and not a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"... | ||
215 | What is the title of the Figure 1 | null | 211 | fgfl0228 | 3 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 1,
"reason": "The image contains a figure illustrating the shell coal gasification process."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score... | ||
227 | What is the title of this? | null | 218 | fsgl0228 | 2 | null | test | [
{
"bbox": [
735,
1428,
1163,
2006
],
"label": "image",
"sub_label": "illustration"
},
{
"bbox": [
1588,
2167,
1939,
2738
],
"label": "image",
"sub_label": "illustration"
},
{
"bbox": [
628,
2917,
1281,
... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The entire page is a document/text, not a single embedded image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
... | ||
57574 | What is the number in parentheses [ ], between the two Tables? | null | 4,484 | hlvj0223 | 53 | null | test | [] | [] | ||
57579 | What is the income tax for 2003? | null | 4,846 | xnbx0223 | 2 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan containing text and tables, not a single embedded photograph or illustration."
},
"LiquidAI/LFM2.5-VL-1.6B": {
... | ||
238 | Which work area is this related? | null | 231 | trhk0037 | 1 | null | test | [] | [] | ||
246 | Who is the third person in CC | null | 232 | fxxj0037 | 6 | null | test | [
{
"bbox": [
933,
1240,
1298,
1372
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The handwr... | ||
257 | How much menthol does KOOL "C" have? | null | 236 | hyhk0037 | 8 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is a document scan, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": ... | ||
46250 | Who is the Medical Monitor or designee? | null | 13,343 | mjbw0217 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"v... | ||
268 | Who signed this? | null | 246 | qqbl0037 | 2 | null | test | [
{
"bbox": [
1220,
1399,
1398,
1464
],
"label": "signature",
"sub_label": "handwritten initials"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The label ... | ||
16653 | What is the purchase order number? | null | 5,264 | rkww0217 | 4 | null | test | [] | [] | ||
277 | What is the average age of camel smoker? | null | 253 | xnbl0037 | 5 | null | test | [] | [] | ||
280 | To whom the letter is addressed? | null | 254 | hjxj0037 | 1 | null | test | [] | [] | ||
286 | What is the heading? | null | 257 | mppk0037 | 1 | null | test | [] | [] | ||
46251 | What is the Manuscript number specified in the 'Title' ? | null | 13,220 | mrdw0217 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The content is a document, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "in... | ||
16673 | What is osteoporosis corelated to? | null | 5,273 | fpbw0217 | 27 | null | test | [] | [] | ||
37507 | What is the value given for girls of 13-15 yrs for 3 months? | null | 10,736 | mqyg0227 | 31 | null | test | [] | [] | ||
63559 | What is the no. of participants in SI group in Miami? | null | 9,300 | gxxh0227 | 8 | null | test | [] | [] | ||
37508 | what is written at the middle of round seal? | null | 10,801 | xgvg0227 | 1 | null | test | [
{
"bbox": [
1052,
726,
1225,
882
],
"label": "image",
"sub_label": "logo"
},
{
"bbox": [
1669,
655,
2072,
1212
],
"label": "image",
"sub_label": "illustration"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "Box #0 contains a logo/seal, which qualifies as an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reas... | ||
301 | For when is startup of the wiegand evaporator system at park 500 is scheduled? | null | 265 | mxxj0037 | 3 | null | test | [] | [] | ||
302 | what is the slope of set #1? | null | 267 | hgbl0037 | 5 | null | test | [] | [] | ||
16690 | What is the name of the company on top of the document ? | null | 5,283 | jycw0217 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The logo at the top is an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is a fa... | ||
310 | At what rate is Methoprene currently added to B&W's tobaccos? | null | 269 | txcj0037 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a small logo/graphic element, which qualifies as an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"scor... | ||
311 | What is the heading of the document? | null | 270 | phxj0037 | 4 | null | test | [] | [] | ||
57663 | What is the Page Number? | null | 5,011 | fqvw0217 | 43 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0.9,
"reason": "The image contains a table, not a chart."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "The imag... | ||
322 | What is cut tobacco no in this page? | null | 276 | lycj0037 | 7 | null | test | [] | [] | ||
327 | what is the title of this page ? | null | 277 | khxj0037 | 6 | null | test | [] | [] | ||
354 | What has to be provided to SULT/SLT development? | null | 286 | hjbl0037 | 2 | null | test | [] | [] | ||
367 | what is the name of this study? | null | 290 | hjbl0037 | 1 | null | test | [] | [] | ||
371 | What is the document number written on the right margin, towards bottom? | null | 294 | fxxj0037 | 3 | null | test | [] | [] | ||
378 | Which company name is provided in the document ? | null | 293 | lycj0037 | 1 | null | test | [] | [] | ||
49540 | which floor details are mentioned in the document? | null | 14,355 | mgbv0228 | 16 | null | test | [] | [] | ||
57739 | What is the Gross Profit for the year ending 2003 (Rs.lac)? | null | 4,862 | znbx0223 | 18 | null | test | [] | [] | ||
57745 | What is the name of the bank? | null | 5,982 | stbm0227 | 17 | null | test | [
{
"bbox": [
1126,
522,
1556,
607
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0.9,
"reason": "The content is a document scan, not an embedded photograph or illustration."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"sco... | ||
403 | What is the heading of the document ? | null | 324 | hjxj0037 | 3 | null | test | [] | [] | ||
57759 | How many meetings of the Audit committee were held in the financial year? | null | 4,820 | tnbx0223 | 15 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan, not a photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "... | ||
16810 | What is the name of the company on the letter head ? | null | 5,319 | fsdw0217 | 5 | null | test | [] | [] | ||
57772 | What % of vests is available for conversion after 3 year? | null | 4,829 | ynbx0223 | 16 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan, not a photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "... | ||
37537 | Which is the first year on x-axis? | null | 10,805 | tkyg0227 | 18 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The image clearly contains a line graph, which fits the definition of a chart."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"s... | ||
57792 | What is the name of the airline? | null | 14,888 | lxkp0227 | 5 | null | test | [
{
"bbox": [
124,
579,
569,
635
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason": "The image ... | ||
49610 | What is the figure number? | null | 14,392 | fmbb0228 | 10 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.98,
"reason": "The image contains a scatter plot, which is a type of chart."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
... | ||
470 | what is the index of shared of the 21-25 segment | null | 307 | rzbj0037 | 6 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a logo/illustration."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is... | ||
57828 | What is the name of the client? | null | 4,886 | hnvw0217 | 13 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The box highlights a small icon/graphic, but the category 'image' is defined as an embedded photograph, illustration, drawing, logo, map, or figure. This icon is too s... | ||
63601 | What is the RDA for Calories for Sedentary woman(1948 report)? | null | 9,332 | gfpg0227 | 19 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "The labe... | ||
57860 | Who is the chairman? | null | 6,148 | snbx0223 | 23 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan, not a photograph, illustration, drawing, logo, map, or figure in the sense of a standalone image."
},
"LiquidAI/LFM2... | ||
57868 | Mr. K. N. Grant, director of ITC, is the chairman of which other company? | null | 6,145 | rnbx0223 | 18 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The top-left corner contains a logo which is an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reaso... | ||
16910 | Which company submitted this document? | null | 5,351 | fpbw0217 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The box #0 is around the text 'EXHIBIT' and 'm 8', which is not a signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"scor... | ||
16913 | What Budget Estimate is given in this document? | null | 5,350 | lzcw0217 | 1 | null | test | [
{
"bbox": [
1225,
1987,
1434,
2081
],
"label": "signature",
"sub_label": "handwritten initials"
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a logo/graphic element which qualifies as an image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
... | ||
57874 | What is the table number? | null | 6,661 | sngx0227 | 9 | null | test | [] | [] | ||
16925 | Who is the sender of the Fax? | null | 5,352 | htdw0217 | 6 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is a document, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "inco... | ||
57911 | What is the heading of the document? | null | 4,579 | pnbx0223 | 149 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan containing financial tables, not a photograph, illustration, drawing, logo, map, or figure in the sense of a standalone image."
... | ||
16955 | What is the Fax no of Karen Mittleman? | null | 5,356 | kyvw0217 | 1 | null | test | [
{
"bbox": [
942,
1438,
1217,
1582
],
"label": "signature",
"sub_label": ""
}
] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box correctly identifies the handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reason... | ||
57917 | Who is the executive chairman? | null | 4,583 | pnbx0223 | 161 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image provided is a document scan, not a standalone image like a photograph or illustration."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incor... | ||
16960 | Which company's fax message is this? | null | 5,359 | lfdw0217 | 12 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is a document, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "inco... | ||
592 | What is the net operating revenue for the year 2010? | null | 356 | lxpj0226 | 6 | null | test | [] | [] | ||
57937 | What is the Priority of Article P2(3)? | null | 4,913 | mkvw0217 | 9 | null | test | [] | [] | ||
57943 | What type of report is this? | null | 4,914 | prvw0217 | 2 | null | test | [] | [] | ||
47340 | What is the Dept.No? | null | 13,808 | nxym0227 | 31 | null | test | [] | [] | ||
57957 | What is the priority of the first Article? | null | 4,917 | mkvw0217 | 7 | null | test | [] | [] | ||
57979 | What is the type of data representation used (graph/table/list)? | null | 4,922 | fqvw0217 | 41 | null | test | [] | [] | ||
57996 | Who are the medical journals for? | null | 4,927 | fyvw0217 | 5 | null | test | [] | [] | ||
653 | By how much percent net operating revenue increased. | null | 375 | lxpj0226 | 7 | null | test | [] | [] | ||
58002 | What is the Strategic Publication Development Budget? | null | 4,929 | lmvw0217 | 3 | null | test | [] | [] | ||
58041 | Who is the client? | null | 4,950 | gkvw0217 | 14 | null | test | [] | [] | ||
58051 | Which university ‘letterhead’ is given? | null | 14,877 | nfnw0228 | 1 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The image is a document scan, not an embedded photograph, illustration, drawing, logo, map, or figure."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": ... | ||
58063 | What is written at the bottom right end of the ‘page’? | null | 5,309 | mlbw0217 | 1 | null | test | [] | [] | ||
58065 | What is the phone number given? | null | 5,298 | rgcw0217 | 1 | null | test | [
{
"bbox": [
1114,
1797,
1283,
1885
],
"label": "image",
"sub_label": "logo"
},
{
"bbox": [
775,
1907,
1012,
1973
],
"label": "image",
"sub_label": "logo"
},
{
"bbox": [
1114,
1907,
1351,
1973
],
... | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "incorrect",
"score": 0,
"reason": "The box covers a large block of text, not a single image."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "correct",
"score": 1,
"reaso... | ||
52251 | What is the amount shown for the recipient ‘Nutrition Fdn.NY’? | null | 14,679 | hgfc0228 | 8 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box correctly highlights a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason... | ||
17155 | What is the Budget estimate for recruit editorial board/monthly newsletter development? | null | 5,404 | xqdw0217 | 42 | null | test | [] | [] | ||
21320 | what is the name of the university ? | null | 6,350 | hnnp0227 | 35 | null | test | [] | [
{
"detection_idx": 0,
"per_judge": {
"google/gemma-4-E4B-it": {
"verdict": "correct",
"score": 0.95,
"reason": "The box contains a handwritten signature."
},
"LiquidAI/LFM2.5-VL-1.6B": {
"verdict": "incorrect",
"score": 0,
"reason": "no verdi... | ||
17160 | What is the client name mentioned in this document? | null | 5,405 | lqcw0217 | 1 | null | test | [] | [] |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- -