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.
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | genai |
| Model | gemini-3.5-flash-lite |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 0.00 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 52.3K IT + 4.8K OT = 57.1K TT | Cost: 0.016$ + 0.012$ = 0.028$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openrouter |
| Model | moonshotai/kimi-k3 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 94.60 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 194.0K IT + 175.8K OT = 369.7K TT | Cost: 0.582$ + 2.636$ = 3.218$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.6-terra |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 94.60 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 158.1K IT + 11.3K OT = 169.4K TT | Cost: 0.395$ + 0.169$ = 0.565$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | genai |
| Model | gemini-3.6-flash |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 90.80 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 52.3K IT + 4.9K OT = 57.2K TT | Cost: 0.078$ + 0.037$ = 0.115$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.6-luna |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 97.20 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 158.1K IT + 21.3K OT = 179.4K TT | Cost: 0.158$ + 0.128$ = 0.286$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.6-sol |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 94.70 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 158.1K IT + 14.2K OT = 172.3K TT | Cost: 0.791$ + 0.426$ = 1.216$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-opus-5 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 88.60 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 213.4K IT + 4.8K OT = 218.2K TT | Cost: 1.067$ + 0.119$ = 1.186$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-fable-5 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 96.00 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 213.6K IT + 4.2K OT = 217.8K TT | Cost: 2.136$ + 0.210$ = 2.346$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-sonnet-5 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 4.80 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 216.6K IT + 4.0K OT = 220.5K TT | Cost: 0.433$ + 0.040$ = 0.473$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | genai |
| Model | gemini-3.1-flash-lite |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 0.00 % |
| Test time | unknown seconds |
Extract all advertisements and return their bounding boxes.
The original size of the page is {width} x {height} pixels.
no valid result
| Fuzzy Score | F1 micro / macro | Micro precision/recall | Tue/False Positives | |||||
| n/a | 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: 52.3K IT + 5.0K OT = 57.4K TT | Cost: 0.013$ + 0.008$ = 0.021$ |