Can Dify turn a clean scan into accurate text?
Dify did not turn the clean scan into accurate text. The scan had no extractable text, yet the document was marked completed and available with a word count, and the lookup returned other records instead of the scan's fact; the Pipeline view was present but unopened.
1 of 1 test case failed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above counts this row.
Fact that exists only as pixelsFailEvidence
“What as-found bias is recorded on calibration certificate C-77413?”
Status: 200 Response body: { "query": { "content": "What as-found bias is recorded on calibration certificate C-77413?" }, "records": [ { "segment": { "id": "bf7724c1-2b89-4fe9-9cb5-09c6c46ad5b4", "position": 6, "document_id": "9ba90c1b-007a-4b5b-91fd-030f45e73bcb", "content": "Calibration\n\nEvery instrument leaves the laboratory with a signed certificate recording the as-found and as-left bias at four reference points across the working range. The recommended recalibration interval for the Tolvan A3 is 22 months from the date of the last certificate. An instrument returned early because of a suspected drift is checked as found before anything is adjusted, so that the drift can be quantified rather than merely corrected.\n\nFirmware", "sign_content": null, "answer": null, "word_count": 460, "tokens": 85, "keywords": [], "index_node_id": "8efd2764-befa-4d64-af98-b766aa1cb3a4", "index_node_hash": "0580a3b7e28d801a55bc838ea0bc0e98e06d80f3fd10dad6733ccdec698d92fc", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789754309, "indexing_at": 1789754309, "completed_at": 1789754312, "error": null, "stopped_at": null, "document": { "id": "9ba90c1b-007a-4b5b-91fd-030f45e73bcb", "data_source_type": "upload_file", "name": "A10_tolvan_a3_product_overview.md", "doc_type": null, "doc_metadata": { "region": "group" } } }, "child_chunks": [], "score": 0.54985493, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "be655143-3a49-4b5f-a130-1ea6abfab1fb", "position": 5, "document_id": "24d8e7b7-2b95-412f-8492-390a47422461", "content": "Drift is a calibration matter, not a defect.\r\n\u2022 Any instrument whose serial number has been removed or altered.\r\n4. Making a claim\r\nA claim is made through the service desk, quoting the serial number and the delivery note. The service\r\ndesk raises a ticket, arranges return carriage and tells the customer within five working days whether the\r\nfailure is covered.", "sign_content": null, "answer": null, "word_count": 363, "tokens": 74, "keywords": [], "index_node_id": "13804d8f-76a5-4980-8544-289d3c32295b", "index_node_hash": "5e26687d25a112c0b0b1552639d9fd7a0ea98678901d405bbef4344c5f4de5a1", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789754298, "indexing_at": 1789754298, "completed_at": 1789754300, "error": null, "stopped_at": null, "document": { "id": "24d8e7b7-2b95-412f-8492-390a47422461", "data_source_type": "upload_file", "name": "A08_warranty_terms_sales_pack.pdf", "doc_type": null, "doc_metadata": { "region": "group" } } }, "child_chunks": [], "score": 0.46607465, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "321f07e2-5765-416b-865b-b9170e8286b1", "position": 5, "document_id": "cd32e6aa-7c16-4d60-bff2-bd7250451958", "content": "Drift is a calibration matter, not a defect.\r\n\u2022 Any instrument whose serial number has been removed or altered.\r\n4. Making a claim\r\nA claim is made through the service desk, quoting the serial number and the delivery note. The service\r\ndesk raises a ticket, arranges return carriage and tells the customer within five working days whether the\r\nfailure is covered.", "sign_content": null, "answer": null, "word_count": 363, "tokens": 74, "keywords": [], "index_node_id": "d15c7f3d-1bea-4f13-863c-b458e9f22f74", "index_node_hash": "5e26687d25a112c0b0b1552639d9fd7a0ea98678901d405bbef4344c5f4de5a1", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789754303, "indexing_at": 1789754306, "completed_at": 1789754306, "error": null, "stopped_at": null, "document": { "id": "cd32e6aa-7c16-4d60-bff2-bd7250451958", "data_source_type": "upload_file", "name": "A09_warranty_statement_service_pack.pdf", "doc_type": null, "doc_metadata": { "region": "group" } } }, "child_chunks": [], "score": 0.46607465, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "38403981-4749-4253-8ae1-30a5b5eaf666", "position": 5, "document_id": "e04044ec-990a-4bf1-9908-34be00b3fa17", "content": "What the depot does not do\n\nThe depot does not calibrate. An instrument that needs a certificate goes to the laboratory, is booked in under its own job number, and comes back to the depot only once the certificate has been signed.\n\nCommissioning: before travelling", "sign_content": null, "answer": null, "word_count": 264, "tokens": 53, "keywords": [], "index_node_id": "137b3abe-fae4-4e77-a17c-33e93fa7db36", "index_node_hash": "13cdf7935207577a55f0bd797e858af534098afc6f667a3c4f3df2b4ca31ef04", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789752857, "indexing_at": 1789752858, "completed_at": 1789752862, "error": null, "stopped_at": null, "document": { "id": "e04044ec-990a-4bf1-9908-34be00b3fa17", "data_source_type": "upload_file", "name": "A05_depot_and_commissioning_note.md", "doc_type": null, "doc_metadata": { "region": "uk" } } }, "child_chunks": [], "score": 0.4369651, "tsne_position": null, "files": [], "summary": null } ] }
| ✗ | Expected: The fact should return; if not, the tool should say there was no text instead of looking complete.Found: The lookup returned other records, not the scan's fact, while the document showed completed, available, and a word count; the stored chunk was only an image link. |
The tool’s response is printed above, under What the tool returned. Show this screenshot
Open original ↗The run needed the fact to return, or a no-text message if it could not. Instead, the lookup missed the scan while the document still showed completed, available, and counted, so it does not meet the needed result.
Word count mask. The status surface reports 87 words for a chunk that is only an image link, so it looks searchable even though no transcript text is stored.
Pipeline left closed. The workspace included a Pipeline section, but it stayed unopened, matching the path used in this run.
The capture does not show the ingestion-time configuration.
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.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
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.
- 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 row says which 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 row 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 | Managed RAG → | 15 scenarios · 7 tools |
| Capability | Data Ingestion → | |
| Scenario | A cleanly scanned document → | |
| Tool | Dify → |
Global scenario definition → · Global capability definition → · Dify 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.
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.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →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.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.