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': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | mistral |
| Model | ministral-8b-2512 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 0.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.00 | 0.00 | 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: 585 IT + 407 OT = 992 TT | Cost: 0.000$ + 0.000$ = 0.000$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | mistral |
| Model | ministral-8b-2512 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 0.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.00 | 0.00 | 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: 585 IT + 415 OT = 1.0K TT | Cost: 0.000$ + 0.000$ = 0.000$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-35b-a3b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 55.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.54 | 0.55 | 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: 280.6K IT + 5.6K OT = 286.2K TT | Cost: 0.070$ + 0.011$ = 0.081$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-397b-a17b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 61.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.56 | 0.61 | 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: 177.6K IT + 3.1K OT = 180.7K TT | Cost: 0.107$ + 0.011$ = 0.118$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-flash-2026-02-23 |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 57.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.51 | 0.57 | 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: 177.6K IT + 3.3K OT = 181.0K TT | Cost: 0.018$ + 0.001$ = 0.019$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-397b-a17b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 58.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.58 | 0.58 | 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: 280.6K IT + 5.3K OT = 285.8K TT | Cost: 0.168$ + 0.019$ = 0.187$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-27b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 59.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.53 | 0.59 | 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: 177.6K IT + 3.1K OT = 180.8K TT | Cost: 0.053$ + 0.007$ = 0.061$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-35b-a3b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 58.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.52 | 0.58 | 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: 177.6K IT + 3.2K OT = 180.9K TT | Cost: 0.044$ + 0.006$ = 0.051$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-122b-a10b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 53.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.61 | 0.53 | 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: 102.9K IT + 1.9K OT = 104.8K TT | Cost: 0.041$ + 0.006$ = 0.047$ |
{'document-type': ['letter'], 'writing': ['typed', 'handwritten'], 'century': [20], 'language': ['de'], 'layout': ['prose'], 'entry-type': ['person', 'location'], 'task': ['information-extraction']}
| Provider | alibaba |
| Model | qwen3.5-122b-a10b |
| Temperature | 0.0 |
| Dataclass | Document |
| Normalized Score | 55.00 % |
| Test time | unknown seconds |
IDENTITY and PURPOSE:
You are presented with a series of images constituting a historical letter. Your task is to extract the
values of the following keys from the letter and return them in a JSON file where the values
corresponding to each key should be stored as a list, even if there is only a single value for a
key:
- letter_title: Title of the letter.
- sender_persons: Name(s) of the person(s) who wrote the letter.
- send_date: The exact or approximate date the letter was written.
- receiver_persons: Name(s) of the person(s) who received the letter.
Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims
and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for
dates. If a piece of information is not included in the letter, set the value for the corresponding key
to "null". Do not return anything except the JSON file.
EXAMPLE:
{
"letter_title": ["Petition for Environmental Protection"],
"send_date": ["1993-03-12"],
"sender_persons": ["Lisa Simpson"],
"receiver_persons": ["Mayor Joe Quimby", "Seymour Skinner"],
}
OUTPUT:
no valid result| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 0.55 | 0.55 | 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: 280.6K IT + 4.4K OT = 285.0K TT | Cost: 0.112$ + 0.014$ = 0.126$ |