A test run is a single execution of a benchmark test using a defined model configuration.
Each run represents how a particular large language model (LLM) — such as GPT-4, Claude-3, or Gemini — performed on a given task at a specific time, with specific settings.
A test run includes:
Together, test runs make it possible to compare models, providers, and configurations across benchmarks in a transparent and reproducible way.
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | x-ai |
| Model | grok-4.3 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 84.50 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.87 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.2K IT + 7.5K OT = 19.7K TT | Cost: 0.015$ + 0.019$ = 0.034$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | openrouter |
| Model | meta-llama/llama-4-scout-17b-16e-instruct |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 53.00 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.57 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 13.0K IT + 5.7K OT = 18.7K TT | Cost: 0.001$ + 0.002$ = 0.003$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | openrouter |
| Model | stepfun/step-3.7-flash-20260528 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 92.00 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.94 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 6.9K IT + 80.5K OT = 87.4K TT | Cost: 0.001$ + 0.093$ = 0.094$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | mistral |
| Model | mistral-small-2506 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 30.20 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.31 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.1K IT + 9.1K OT = 21.2K TT | Cost: 0.001$ + 0.003$ = 0.004$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | mistral |
| Model | pixtral-large-2411 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 78.80 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.81 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.1K IT + 9.5K OT = 21.6K TT | Cost: 0.024$ + 0.057$ = 0.081$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | mistral |
| Model | magistral-small-2509 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 11.80 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.12 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 2.7K IT + 2.1K OT = 4.8K TT | Cost: 0.001$ + 0.003$ = 0.004$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | openrouter |
| Model | qwen/qwen3.7-plus-20260602 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 78.10 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.83 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.2K IT + 20.7K OT = 32.9K TT | Cost: 0.005$ + 0.033$ = 0.038$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | mistral |
| Model | mistral-large-2512 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 78.20 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.80 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.1K IT + 10.0K OT = 22.1K TT | Cost: 0.006$ + 0.015$ = 0.021$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | mistral |
| Model | mistral-medium-2505 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 50.60 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.52 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 12.1K IT + 6.8K OT = 19.0K TT | Cost: 0.005$ + 0.014$ = 0.019$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [18, 19], 'language': ['de'], 'layout': ['prose'], 'script-style': ['fraktur'], 'task': ['transcription']}
| Provider | anthropic |
| Model | claude-opus-4-8 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 78.40 % |
| Test time | unknown seconds |
## IDENTITY AND PURPOSE
You are an OCR and information extraction system trained to process historical newspaper pages printed in 18th-century German using Fraktur type. The pages contain mostly classified advertisements. Your task is to identify and extract each advertisement *exactly as printed*, including historical spellings, typographic errors, punctuation, and formatting.
## INSTRUCTIONS
- Extract **all advertisements** from the input image, one after the other, following the sequence on the page.
- Maintain the **original spelling**, capitalization, and any **typos or non-standard forms**.
- Follow these transcription rules:
- the long s (ſ) is transcribed as "s"
- "/" is transcribed as ","
- Use the masthead of the newspaper only to extract the date, ignore other content.
- The layout is typically **two-column**; extract ads from both columns, including the ad number.
- Return the result as a **JSON object** in the specified format and **nothing else** (no explanations, summaries, or additional text).
- For each advertisement, include:
- `"date"`: the publication date of the page in ISO 8061 format (YYYY-MM-DD)
- `"tags_section"`: the heading under which the advertisement appears
- `"text"`: the full advertisement text
## EXAMPLE OUTPUT
{
"advertisements": [
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "5. Ein kleines, jedoch listiges Lehrbuch der Zauberkunst, lange im Gebrauche des jungen Bartolomeus Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zum Verkauff offeriert",
"text": "6. Ein rarer, mit Edelsteinen besetzter Saxophon-Kasten, aus dem Besitze der Jungfer Lisa Simpson."
},
{
"date": "1731-01-02",
"tags_section": "Es werden zu Entleihen begehrt",
"text": "7. Ein gar prachtvoller, jedoch etwas zerlesener Band mit Rezepten von Margaretha Simpsonin."
}
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| 0.79 | n/a | n/a | n/a | n/a | n/a | n/a | n/a | n/a |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 19.0K IT + 15.1K OT = 34.2K TT | Cost: 0.095$ + 0.379$ = 0.474$ |