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 | anthropic |
| Model | claude-haiku-4-5-20251001 |
| 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: 111.4K IT + 4.3K OT = 115.7K TT | Cost: 0.111$ + 0.022$ = 0.133$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-sonnet-4-20250514 |
| 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: 98.8K IT + 4.1K OT = 102.9K TT | Cost: 0.296$ + 0.062$ = 0.358$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-opus-4-1-20250805 |
| 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: 98.8K IT + 4.4K OT = 103.2K TT | Cost: 1.482$ + 0.328$ = 1.810$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | genai |
| Model | gemini-3-flash-preview |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 84.80 % |
| 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 + 3.2K OT = 55.5K TT | Cost: 0.026$ + 0.010$ = 0.036$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | contour_local |
| Model | opencv-contour |
| Temperature | not set (=0.5) |
| Dataclass | MagazinePage |
| Normalized Score | 80.20 % |
| Test time | unknown seconds |
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: 534.7K IT + 3.5K OT = 538.2K TT | Cost: 0.000$ + 0.000$ = 0.000$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-4o-2024-08-06 |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 39.80 % |
| 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: 60.0K IT + 1.7K OT = 61.8K TT | Cost: 0.150$ + 0.017$ = 0.167$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-sonnet-4-6 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 3.30 % |
| 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: 111.4K IT + 3.6K OT = 115.0K TT | Cost: 0.334$ + 0.054$ = 0.389$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5-2025-08-07 |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 78.70 % |
| 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: 51.0K IT + 104.1K OT = 155.0K TT | Cost: 0.064$ + 1.041$ = 1.104$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.4-2026-03-05 |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 70.90 % |
| 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: 136.7K IT + 2.2K OT = 138.9K TT | Cost: 0.342$ + 0.034$ = 0.375$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.3-codex |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 86.00 % |
| 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: 92.2K IT + 2.1K OT = 94.3K TT | Cost: 0.161$ + 0.029$ = 0.191$ |