Document Extraction Comparator – Findings Report

24 PDFs tested . Judge: gpt-5.4 Generated 2026-03-11

Overall Extractor Leaderboard

ExtractorAvg ScoreWinsPDFs TestedAvg Time (s)
llm_direct4.31202428.0
marker3.67014.0
mineru3.50142.2
docling3.480245.1
pymupdf4llm3.362240.9
markitdown3.331240.5
unstructured3.0212310.3

llm_direct ranked highest overall with an average score of 4.31 across 24 documents, winning 20 of 24 head-to-head comparisons. However, it averaged 28.0s per document. The fastest extractor was markitdown at 0.5s average, scoring 3.33 overall.

2022-Lobo-Softball-Schedule.pdf

Winner: llm_direct (avg 5.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555555.007.0
docling4232453.333.5
unstructured2222242.332.3
markitdown1111151.670.0
pymupdf4llm1111151.670.7

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` .

2024-25_District_Calendar.pdf

Winner: llm_direct (avg 4.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4453354.0016.2
markitdown3232342.830.1
docling2233222.339.8
unstructured2232322.332.1
pymupdf4llm2221242.170.5

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

2025-2026_SHUTTLE_BUSES.pdf

Winner: llm_direct (avg 5.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555555.007.6
docling4355454.331.7
unstructured3225453.501.7
pymupdf4llm2225353.170.2
markitdown2121342.170.1

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key, :

4-STRATEGIC-PLAN.pdf

Winner: llm_direct (avg 4.7)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5455454.679.3
markitdown3334423.170.1
docling3333322.8310.0
unstructured2223312.1712.1
pymupdf4llm1111131.330.4

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

CPSD_2024-2025_Transportation_Snow_Routes.pdf

Winner: llm_direct (avg 5.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555555.0019.4
docling4454454.336.2
pymupdf4llm4454534.170.4
markitdown4332423.000.2
unstructured3231342.676.6

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`

CSL_Webpage_Design.pdf

Winner: llm_direct (avg 4.7)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5455454.675.1
markitdown4445354.170.2
pymupdf4llm3335443.670.2
unstructured3235323.002.2
docling2225232.672.4

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

DPS-Calendar-2026-27_ENGLISH.pdf

Winner: pymupdf4llm (avg 3.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
pymupdf4llm3332343.000.5
llm_direct3341253.009.2
markitdown2221342.330.2
docling2211242.002.4
unstructured1221231.833.3

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`

DPS-Calendar-2026-27_FRENCH.pdf

Winner: llm_direct (avg 3.7)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct3452353.6733.5
pymupdf4llm3231332.500.5
markitdown2221342.330.3
docling2221232.002.6
unstructured2231121.833.4

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`

Denver_Schools_Thrive_Initiative_Regional_Meet.pdf

Winner: llm_direct (avg 4.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555454.839.7
docling4455454.502.6
markitdown4355434.000.4
pymupdf4llm4455424.000.2
unstructured3355423.673.9

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` .

Director_Sia_Community_Engagement.pdf

Winner: llm_direct (avg 3.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4453343.8331.2
markitdown4453323.500.3
docling3334323.009.8
pymupdf4llm3342322.831.2
unstructured3342322.8325.6

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` .

English_One_Pager_for_New_Families.pdf

Winner: llm_direct (avg 4.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5454454.507.8
docling4453444.002.4
unstructured4342453.672.2
pymupdf4llm4342433.330.3
markitdown2232342.670.1

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

FAQ_School_Choice_OSCPE.pdf

Winner: llm_direct (avg 4.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555524.508.0
pymupdf4llm4455534.330.2
docling4455344.172.4
markitdown4345423.670.1
unstructured3245423.333.9

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

Graduation_Requirements_584.10.pdf

Winner: llm_direct (avg 4.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5554534.507.5
docling4454544.332.0
markitdown5454534.330.1
pymupdf4llm5454524.170.2
unstructured4343423.333.6

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`

LRSD_Ready_for_Learning_Plan_FY23.pdf

Winner: pymupdf4llm (avg 3.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
pymupdf4llm4453323.502.1
markitdown4443323.332.2
docling3332322.6711.7
unstructured3342222.6747.7
llm_direct3441132.6728.0

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` .

Lady_Lobo_Volleyball_Booster_Club_Membership.pdf

Winner: llm_direct (avg 4.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5455554.836.3
pymupdf4llm3345343.670.2
docling3345423.503.0
markitdown3225443.330.2
unstructured3335333.332.1

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` .

Lobo_Student-Athlete_Discipline_Policy.pdf

Winner: llm_direct (avg 4.7)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5455454.676.4
docling4455454.503.1
markitdown4455454.500.1
pymupdf4llm4455454.500.2
unstructured4355544.332.1

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`

Private_Lesson_Scholarship_Application.pdf

Winner: llm_direct (avg 5.0)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct5555555.005.7
markitdown5455554.830.1
pymupdf4llm5455554.830.3
unstructured5355454.501.8
docling4454454.333.2

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

RI.1_Equity.pdf

Winner: llm_direct (avg 3.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4453433.8330.7
docling4443433.674.6
markitdown4443433.670.9
pymupdf4llm4342433.330.8
unstructured3342333.0011.7

marker: In order to use GoogleGeminiService, you must set the configuration values gemini_api_key, :

Retirement_of_Dr_James_Wilcox.pdf

Winner: llm_direct (avg 4.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4455454.507.1
pymupdf4llm3345433.670.2
docling3325433.334.1
markitdown2225343.000.4
unstructured2215322.502.4

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,` :

Short_History_of_the_LRSD.pdf

Winner: unstructured (avg 4.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
unstructured5455554.833.3
llm_direct5455554.838.9
docling4455554.671.9
pymupdf4llm4455554.670.2
markitdown4455534.330.1

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

Student_Handbook_GCB.pdf

Winner: llm_direct (avg 4.5)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4454554.5074.8
docling4453544.175.9
pymupdf4llm4453523.831.1
markitdown4342423.170.7
unstructured3342333.0024.2

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`.

Wellness-Committee-Member-2025-2026.pdf

Winner: llm_direct (avg 4.3)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct4454454.337.1
docling3343453.675.7
markitdown3342453.500.1
pymupdf4llm4342433.330.3
unstructured4231353.002.8

marker: In order to use GoogleGeminiService, you must set the configuration values gemini_api_key, .

txschools-one-pager-25-web.pdf

Winner: markitdown (avg 4.3)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
markitdown4455354.330.1
llm_direct4455354.335.0
marker3345253.678.6
mineru3345243.5042.2
pymupdf4llm3325343.330.2
docling2335323.002.8

unstructured: Unknown model type: layout_v1.0.0

voice-winter2025-digital.pdf

Winner: llm_direct (avg 2.8)

Extractortext_accuracystructure_preservationreading_ordertable_fidelitycompletenessnoise_artifactsAvgTime (s)
llm_direct2333242.83319.6
docling2222322.1719.1
markitdown2222312.005.3
unstructured1222311.8375.7
pymupdf4llm2211221.6710.6

marker: In order to use GoogleGeminiService, you must set the configuration values `gemini_api_key,`