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 | genai |
| Model | gemini-2.0-flash-lite |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 50.87 % |
| 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 | 0.50 | 0.50 | 15 | 498 | 494 | 494 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 33.8K IT + 16.6K OT = 50.4K TT | Cost: 0.003$ + 0.005$ = 0.008$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-2.5-pro |
| 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 | 0.51 | 0.51 | 0.51 | 0.51 | 15 | 508 | 486 | 484 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 9.9K IT + 16.8K OT = 26.7K TT | Cost: 0.012$ + 0.168$ = 0.180$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-2.0-flash |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 41.00 % |
| 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 | 0.42 | 0.41 | 0.41 | 0.42 | 15 | 420 | 597 | 572 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 28.2K IT + 16.0K OT = 44.2K TT | Cost: 0.003$ + 0.006$ = 0.009$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-2.5-flash |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 48.27 % |
| 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 | 0.48 | 0.47 | 0.49 | 15 | 484 | 541 | 508 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 4.3K IT + 12.3K OT = 16.5K TT | Cost: 0.001$ + 0.031$ = 0.032$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-2.5-flash |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 50.87 % |
| 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 | 0.51 | 0.52 | 0.52 | 15 | 514 | 479 | 478 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 9.9K IT + 13.8K OT = 23.7K TT | Cost: 0.003$ + 0.035$ = 0.038$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | anthropic |
| Model | claude-sonnet-4-5-20250929 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 38.40 % |
| 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 | 0.39 | 0.38 | 0.38 | 0.40 | 15 | 395 | 646 | 597 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 35.8K IT + 16.7K OT = 52.5K TT | Cost: 0.107$ + 0.250$ = 0.358$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | mistral |
| Model | mistral-large-2411 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 0.00 % |
| 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 | 0.00 | 0.00 | 0.00 | 0.00 | 15 | 0 | 0 | 992 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 9.0K IT + 18.7K OT = 27.8K TT | Cost: 0.018$ + 0.112$ = 0.131$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | mistral |
| Model | magistral-medium-2509 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 0.00 % |
| 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 | 0.00 | 0.00 | 0.00 | 0.00 | 15 | 0 | 20 | 992 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 8.2K IT + 827 OT = 9.0K TT | Cost: 0.016$ + 0.004$ = 0.021$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | genai |
| Model | gemini-2.5-flash-lite |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 39.00 % |
| 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 | 0.39 | 0.36 | 0.39 | 15 | 390 | 693 | 602 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 4.3K IT + 17.7K OT = 21.9K TT | Cost: 0.000$ + 0.007$ = 0.007$ |
{'document-type': ['book-page'], 'writing': ['printed'], 'century': [20], 'language': ['en', 'de'], 'layout': ['list'], 'entry-type': ['company'], 'task': ['information-extraction']}
| Provider | mistral |
| Model | mistral-medium-2505 |
| Temperature | 0.5 |
| Dataclass | ListPage |
| Normalized Score | 0.00 % |
| 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 | 0.00 | 0.00 | 0.00 | 0.00 | 15 | 0 | 150 | 992 |
| Micro Precision | Micro Recall | Instances | TP | FP | FN | |||
| Pricing Date: n/a, n/a. | Tokens: 3.0K IT + 1.8K OT = 4.7K TT | Cost: 0.001$ + 0.004$ = 0.005$ |