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': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openai |
| Model | gpt-5.6-terra |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 53.20 % |
| Test time | unknown seconds |
The image you are presented with stems from a digitized book containing lists of companies.
Your task is to extract structured information about each company listed on the page.
About the source:
- The image stems from a trade index of the British Swiss Chamber of Commerce.
- The image can show an alphabetical or a thematic list of companies.
- The companies are mostly located in Switzerland and the UK.
- The image stems from a trade index between 1925 and 1958.
- Most pages have one column but some years have two columns.
- The source itself is in English and German but the company names can be in English, German, French or Italian.
About the entries:
- Each entry describes a single company or person.
- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.
- Alphabetical entries seldom to never have locations.
- Thematic entries often have locations.
- Thematic entries are listed under headings that describe the type of business.
- Some thematic headings are only references to other headings, e.g. "X, s. Y".
About the output:
- Answer in valid JSON. The JSON should be an array of objects with the following fields:
- The page ID is given as {page_id}.
- Do not add country information, if it is not directly written with the location.
{
"entry_id": "A unique identifier for the entry, e.g. '{page_id}-1'",
"company_name": "The name of the company or person",
"location": "The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null."
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.52 | 0.53 | 0.52 | 0.52 | 15 | 517 | 471 | 475 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 53.4K IT + 15.4K OT = 68.8K TT | Cost: 0.134$ + 0.231$ = 0.365$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openai |
| Model | gpt-5.6-sol |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 52.13 % |
| Test time | unknown seconds |
The image you are presented with stems from a digitized book containing lists of companies.
Your task is to extract structured information about each company listed on the page.
About the source:
- The image stems from a trade index of the British Swiss Chamber of Commerce.
- The image can show an alphabetical or a thematic list of companies.
- The companies are mostly located in Switzerland and the UK.
- The image stems from a trade index between 1925 and 1958.
- Most pages have one column but some years have two columns.
- The source itself is in English and German but the company names can be in English, German, French or Italian.
About the entries:
- Each entry describes a single company or person.
- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.
- Alphabetical entries seldom to never have locations.
- Thematic entries often have locations.
- Thematic entries are listed under headings that describe the type of business.
- Some thematic headings are only references to other headings, e.g. "X, s. Y".
About the output:
- Answer in valid JSON. The JSON should be an array of objects with the following fields:
- The page ID is given as {page_id}.
- Do not add country information, if it is not directly written with the location.
{
"entry_id": "A unique identifier for the entry, e.g. '{page_id}-1'",
"company_name": "The name of the company or person",
"location": "The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null."
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.52 | 0.52 | 0.53 | 0.52 | 15 | 518 | 467 | 474 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 53.4K IT + 17.4K OT = 70.8K TT | Cost: 0.267$ + 0.522$ = 0.789$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | anthropic |
| Model | claude-opus-5 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 36.53 % |
| Test time | unknown seconds |
- Answer in valid JSON.
- The page ID is given as {page_id}.
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.38 | 0.37 | 0.36 | 0.39 | 15 | 388 | 683 | 604 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 65.8K IT + 18.8K OT = 84.6K TT | Cost: 0.329$ + 0.470$ = 0.799$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openai |
| Model | gpt-5.6-terra |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 48.40 % |
| Test time | unknown seconds |
- Answer in valid JSON.
- The page ID is given as {page_id}.
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.49 | 0.48 | 0.49 | 0.49 | 15 | 487 | 503 | 505 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 48.3K IT + 14.5K OT = 62.8K TT | Cost: 0.121$ + 0.217$ = 0.338$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openrouter |
| Model | moonshotai/kimi-k3 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 47.47 % |
| Test time | unknown seconds |
- Answer in valid JSON.
- The page ID is given as {page_id}.
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.48 | 0.47 | 0.48 | 0.48 | 15 | 472 | 519 | 520 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 59.6K IT + 48.0K OT = 107.7K TT | Cost: 0.167$ + 0.666$ = 0.890$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-3.5-flash-lite |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 46.80 % |
| Test time | unknown seconds |
- Answer in valid JSON.
- The page ID is given as {page_id}.
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.47 | 0.47 | 0.46 | 0.47 | 15 | 471 | 554 | 521 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 16.7K IT + 15.3K OT = 32.1K TT | Cost: 0.005$ + 0.038$ = 0.043$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | anthropic |
| Model | claude-opus-5 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 41.07 % |
| Test time | unknown seconds |
The image you are presented with stems from a digitized book containing lists of companies.
Your task is to extract structured information about each company listed on the page.
About the source:
- The image stems from a trade index of the British Swiss Chamber of Commerce.
- The image can show an alphabetical or a thematic list of companies.
- The companies are mostly located in Switzerland and the UK.
- The image stems from a trade index between 1925 and 1958.
- Most pages have one column but some years have two columns.
- The source itself is in English and German but the company names can be in English, German, French or Italian.
About the entries:
- Each entry describes a single company or person.
- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.
- Alphabetical entries seldom to never have locations.
- Thematic entries often have locations.
- Thematic entries are listed under headings that describe the type of business.
- Some thematic headings are only references to other headings, e.g. "X, s. Y".
About the output:
- Answer in valid JSON. The JSON should be an array of objects with the following fields:
- The page ID is given as {page_id}.
- Do not add country information, if it is not directly written with the location.
{
"entry_id": "A unique identifier for the entry, e.g. '{page_id}-1'",
"company_name": "The name of the company or person",
"location": "The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null."
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.41 | 0.41 | 0.39 | 0.42 | 15 | 418 | 653 | 574 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 72.9K IT + 19.5K OT = 92.4K TT | Cost: 0.365$ + 0.488$ = 0.852$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-3.5-flash-lite |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 50.93 % |
| Test time | unknown seconds |
The image you are presented with stems from a digitized book containing lists of companies.
Your task is to extract structured information about each company listed on the page.
About the source:
- The image stems from a trade index of the British Swiss Chamber of Commerce.
- The image can show an alphabetical or a thematic list of companies.
- The companies are mostly located in Switzerland and the UK.
- The image stems from a trade index between 1925 and 1958.
- Most pages have one column but some years have two columns.
- The source itself is in English and German but the company names can be in English, German, French or Italian.
About the entries:
- Each entry describes a single company or person.
- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.
- Alphabetical entries seldom to never have locations.
- Thematic entries often have locations.
- Thematic entries are listed under headings that describe the type of business.
- Some thematic headings are only references to other headings, e.g. "X, s. Y".
About the output:
- Answer in valid JSON. The JSON should be an array of objects with the following fields:
- The page ID is given as {page_id}.
- Do not add country information, if it is not directly written with the location.
{
"entry_id": "A unique identifier for the entry, e.g. '{page_id}-1'",
"company_name": "The name of the company or person",
"location": "The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null."
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.50 | 0.51 | 0.49 | 0.51 | 15 | 502 | 513 | 490 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 22.3K IT + 17.2K OT = 39.5K TT | Cost: 0.007$ + 0.043$ = 0.050$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openai |
| Model | gpt-5.6-luna |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 54.20 % |
| Test time | unknown seconds |
The image you are presented with stems from a digitized book containing lists of companies.
Your task is to extract structured information about each company listed on the page.
About the source:
- The image stems from a trade index of the British Swiss Chamber of Commerce.
- The image can show an alphabetical or a thematic list of companies.
- The companies are mostly located in Switzerland and the UK.
- The image stems from a trade index between 1925 and 1958.
- Most pages have one column but some years have two columns.
- The source itself is in English and German but the company names can be in English, German, French or Italian.
About the entries:
- Each entry describes a single company or person.
- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.
- Alphabetical entries seldom to never have locations.
- Thematic entries often have locations.
- Thematic entries are listed under headings that describe the type of business.
- Some thematic headings are only references to other headings, e.g. "X, s. Y".
About the output:
- Answer in valid JSON. The JSON should be an array of objects with the following fields:
- The page ID is given as {page_id}.
- Do not add country information, if it is not directly written with the location.
{
"entry_id": "A unique identifier for the entry, e.g. '{page_id}-1'",
"company_name": "The name of the company or person",
"location": "The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null."
]
}
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.54 | 0.54 | 0.54 | 0.54 | 15 | 536 | 453 | 456 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 53.4K IT + 17.4K OT = 70.8K TT | Cost: 0.053$ + 0.104$ = 0.158$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | openai |
| Model | gpt-5.6-sol |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 45.73 % |
| Test time | unknown seconds |
- Answer in valid JSON.
- The page ID is given as {page_id}.
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.47 | 0.46 | 0.46 | 0.47 | 15 | 470 | 550 | 522 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 48.3K IT + 16.2K OT = 64.5K TT | Cost: 0.242$ + 0.485$ = 0.726$ |