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 | mistral |
| Model | mistral-small-2506 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 6.60 % |
| 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: 11.7K IT + 8.7K OT = 20.4K TT | Cost: 0.001$ + 0.003$ = 0.004$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | genai |
| Model | gemini-2.5-flash-lite-preview-09-2025 |
| 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: 13.9K IT + 5.4K OT = 19.4K TT | Cost: 0.001$ + 0.002$ = 0.004$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-opus-4-5-20251101 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 5.40 % |
| 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 + 3.7K OT = 115.0K TT | Cost: 0.557$ + 0.092$ = 0.649$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openai |
| Model | gpt-5.2-2025-12-11 |
| Temperature | 1.0 |
| Dataclass | MagazinePage |
| Normalized Score | 88.50 % |
| 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: 90.4K IT + 2.3K OT = 92.7K TT | Cost: 0.158$ + 0.032$ = 0.190$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | mistral |
| Model | mistral-large-2411 |
| 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: 12.3K IT + 25.7K OT = 37.9K TT | Cost: 0.025$ + 0.154$ = 0.178$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-sonnet-4-5-20250929 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 2.20 % |
| 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: 111.4K IT + 4.4K OT = 115.8K TT | Cost: 0.334$ + 0.066$ = 0.400$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | openrouter |
| Model | qwen/qwen3-vl-8b-thinking |
| 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: 128.5K IT + 4.8K OT = 133.3K TT | Cost: 0.015$ + 0.006$ = 0.022$ |
{'century': [20], 'document-type': ['newspaper-page'], 'language': ['en'], 'layout': ['prose', 'columns'], 'script': ['latin'], 'task': ['document-understanding'], 'writing': ['printed']}
| Provider | anthropic |
| Model | claude-opus-4-6 |
| Temperature | 0.0 |
| Dataclass | MagazinePage |
| Normalized Score | 21.50 % |
| 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 + 3.8K OT = 115.2K TT | Cost: 0.557$ + 0.096$ = 0.653$ |
{'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 | mistral |
| Model | ministral-14b-2512 |
| 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: 11.7K IT + 506 OT = 12.2K TT | Cost: 0.002$ + 0.000$ = 0.002$ |