AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 16 November 2026

Can GPT-5.6 terra read a cleanly scanned document accurately?

GPT-5.6 terra accurately turned the clean, image-only certificate into Markdown without inventing text. The letter's wording, figures and dates were preserved, and the handwritten signature was marked as an image rather than guessed.

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.

Clean scan — text recoveredPassEvidence
What we sent

We sent the complete image-only laboratory certificate to the OpenAI Responses API as a file in one synchronous request.

InputDocument (PDF)
Input PDF: the image-only laboratory certificate
Open the PDF ↗
What the tool returned

Kirkhollow Analytical Laboratories Ltd

Braithe Road, Vardenne BR7 2HD
01632 960118 · reception@kirkhollow-labs.example


Ms R. Sandiman
Braithe Estuary Partnership
Estuary House, Vardenne Quay
Braithe BR3 4LN

Our reference: KAL-11938/26
Date of report: 4 February 2026

Certificate of analysis

Dear Ms Sandiman

Thank you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.

Sampling pointVardenne Channel, station VQ1
Date and time of sampling27 January 2026, 09:40
Total suspended solids41.6 mg/l (method KAL-M04)
Chloride18,200 mg/l (method KAL-M11)
Ammoniacal nitrogen0.42 mg/l (method KAL-M12)
Dissolved organic carbon5.9 mg/l (method KAL-M22)

The suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow Sands, and the result is consistent with that.

The remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to keep them.

Yours sincerely

[Image: signature]

Dr A. J. Prosser
Laboratory Manager

Show the reply as returned (Markdown)
# Kirkhollow Analytical Laboratories Ltd

Braithe Road, Vardenne BR7 2HD  
01632 960118 · reception@kirkhollow-labs.example

---

Ms R. Sandiman  
Braithe Estuary Partnership  
Estuary House, Vardenne Quay  
Braithe BR3 4LN

Our reference: KAL-11938/26  
Date of report: 4 February 2026

## Certificate of analysis

Dear Ms Sandiman

Thank you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.

|  |  |
|---|---|
| Sampling point | Vardenne Channel, station VQ1 |
| Date and time of sampling | 27 January 2026, 09:40 |
| Total suspended solids | 41.6 mg/l (method KAL-M04) |
| Chloride | 18,200 mg/l (method KAL-M11) |
| Ammoniacal nitrogen | 0.42 mg/l (method KAL-M12) |
| Dissolved organic carbon | 5.9 mg/l (method KAL-M22) |

The suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow Sands, and the result is consistent with that.

The remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to keep them.

Yours sincerely

[Image: signature]

Dr A. J. Prosser  
Laboratory Manager

API response: the assistant's Markdown, effective settings and completion status

Copied from Output file (JSON), output 2 › content 1 › text

Open the whole JSON file ↗
Output file (Markdown)
Returned Markdown: certificate text and the six-row results table
Markdown40 lines
# Kirkhollow Analytical Laboratories Ltd

Braithe Road, Vardenne BR7 2HD  
01632 960118 · reception@kirkhollow-labs.example

---

Ms R. Sandiman  
Braithe Estuary Partnership  
Estuary House, Vardenne Quay  
Braithe BR3 4LN

Our reference: KAL-11938/26  
Date of report: 4 February 2026

## Certificate of analysis

Dear Ms Sandiman

Thank you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.

|  |  |
|---|---|
| Sampling point | Vardenne Channel, station VQ1 |
| Date and time of sampling | 27 January 2026, 09:40 |
| Total suspended solids | 41.6 mg/l (method KAL-M04) |
| Chloride | 18,200 mg/l (method KAL-M11) |
| Ammoniacal nitrogen | 0.42 mg/l (method KAL-M12) |
| Dissolved organic carbon | 5.9 mg/l (method KAL-M22) |

The suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow Sands, and the result is consistent with that.

The remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to keep them.

Yours sincerely

[Image: signature]

Dr A. J. Prosser  
Laboratory Manager
Open the Markdown file ↗
Expected vs. Found
✓Expected: Recover the visible text accurately.Found: It reproduced the source's figures—41.6, 18,200, 0.42 and 5.9 mg/l—and dates: 27 January 2026, 09:40; 4 February 2026; 4 March 2026.
Supporting proof
Proof 1Screenshot
Comparison image: the scanned certificate beside the returned Markdown
Open original ↗
Proof 2Screenshot
Run details: PDF input, default settings, completion status and conversion time
Open original ↗
Cited values1 value from this file
usage
{ "input_tokens": 3281, "input_tokens_details": { "cache_write_tokens": 3278, "cached_tokens": 0 }, "output_tokens": 542, "output_tokens_details": { "reasoning_tokens": 168 }, "total_tokens": 3823 }
Why this result

The text was recovered character-exactly from an image-only page. The small grey footer was omitted, but the benchmark treats it as page furniture that a conversion may drop, so it does not count against the product.

Also observed in this test case

Results stay paired. The certificate's results block became a two-column Markdown table, with each of its six labels beside its own value.

Tested by Chandresh Bisht · evidence dated 23 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
GPT-5.6 terra
Build or version
gpt-5.6-terra
Plan or tier
OpenAI API, credit-funded key (reference subject)
Surface
API
Set up before the run
The complete, clearly scanned laboratory certificate, with ordinary letter text and a results block but no text layer, was to be converted to Markdown in one pass using default settings without tool-specific tuning.
Conversion instruction
PDF to Markdown, version 1
Pipeline
single pass
Tested
23 September 2026 · Chandresh Bisht

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.

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
17 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 →
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/pdf-to-markdown-apis/results/gpt-5-6-terra/a-cleanly-scanned-document · 1 pass · 0 fail · coverage 1/1 · graded 2026-11-16

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 · 747 KB
Output file (Markdown) ↗text/markdown · 1 KB
Proof 1 · Screenshot ↗image/png · 818 KB
Output file (JSON) ↗application/json · 6 KB
Proof 2 · Screenshot ↗image/png · 68 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)a459554d58b9480b19bb3a63598c500b961c3ad377492d18ff227bb439e1f68c
Output file (Markdown)d4dadc402c848c6636b93408cc5342861d5a689faa8a91c831ab1901719f39e1
Proof 1 · Screenshotb669fc8d860b5a9e939cfc3d66a6563bd388e92e2d3104f06ef43c02fc7f574d
Output file (JSON)fd8c3f5008e860159abd3fdd72bb7ddfe1ac3e539999ff6e77153ca88627d309
Proof 2 · Screenshote75b7aa3be1735f0aa36d6ce5398266eae5ab3d2d0157c3a81a3969d43803d68