AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 21 October 2026

Can RAGFlow turn a cleanly scanned document into accurate text?

RAGFlow recovered the requested fact from an image-only calibration certificate. Its first-ranked result contained an as-found bias of -0.037 psu, matching the reference value of -0.037 psu.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
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.

Fact that exists only as pixelsPassEvidence
What we sent

“What as-found bias is recorded on calibration certificate C-77413?”

What the tool returned
Text
As-found bias, mean of four points: -0.037 psu As-left bias,mean of four points:-0.004psu Expanded uncertainty (k = 2): 0.008 psu The instrument was adjusted after the as-found check and passed.

Text log: extracted certificate text, the retrieval request and the full ranked response

Copied from Output file (text), lines 44–68 · an excerpt

Open the whole text file ↗

Source excerpt · partial file · response 1

Text

===== rank 1 | similarity=0.3605 vector=0.8028 term=0.1710 | doc=A03_calibration_certificate_scan.pdf =====

CALIBRATION CERTIFICATE
Fenwake Instruments Ltd
Certificate C-77413
Calibration laboratoryAvonmouth,Bristol S11
SERIAL NUMBER
INSTRUMENT
FW-A3-40871
Tolvan A3 conductivity-temperature sensor
ORDER REFERENCE
CUSTOMER
SEMP/PO/9134
Severn Estuary Monitoring Partnership
NEXT CALIBRATION DUE
DATE OF CALIBRATION
3January 2028
3March 2026
AMBIENT
PROCEDURE
20.4 C, 61 % RH
FWLCAL-114,isSue
Results
Salinityhanhd ainstrncetandard ou

Copied from Output file (text), lines 44–68 · an excerpt

Expected vs. Found
✓Expected: Return the certificate’s as-found bias of -0.037 psu; otherwise say the document yielded no text rather than presenting the collection as complete.Found: The first-ranked result contained an as-found bias of -0.037 psu, matching the certificate’s reference value of -0.037 psu.
Supporting proof
Proof 1Screenshot
Notebook screenshot: the question, first-ranked certificate line and remaining result scores
Open original ↗
Why this result

The requested fact was recovered from the scan in both stored text and the first-ranked result. Visible OCR damage establishes that the text came from pixels, not a hidden text layer; the original scan itself is not attached.

Also observed in this test case

Separate results table. The certificate’s results table was stored as a separate passage and returned at rank 3, carrying four as-found readings: 4.961, 14.964, 24.962 and 34.965 psu.

Tested by Vivek Tomar · evidence dated 21 October 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
RAGFlow
Build or version
v0.26.4
Plan or tier
Starter
Surface
API
Set up before the run
The scanned calibration certificate had to contain the as-found bias of -0.037 psu solely as pixels, with no hidden text layer. It was to be ingested as supplied, then queried for that bias.
Tested
21 October 2026 · Vivek Tomar

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.

LevelNameScope
BenchmarkManaged RAG →15 scenarios · 9 tools
CapabilityData Ingestion →
ScenarioA cleanly scanned document →
ToolRAGFlow →

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.

from the publication record
13 November 2026First publishedManaged RAG 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 →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
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/managed-rag/results/ragflow/a-cleanly-scanned-document · 1 pass · 0 fail · coverage 1/1 · graded 2026-10-21

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.

Output file (text) ↗text/plain; charset=utf-8 · 27 KB
Proof 1 · Screenshot ↗image/png · 306 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Output file (text)f6de4e95e0f48ef1b9f427fa9ac83a2dbe438a67ab1f86767f883246fb3452dd
Proof 1 · Screenshotbcf9baab04542e8c9f2c7f40d5686bf4a751c6d8c5ef458f9633955bc1ee3efc