Ranking
BM25 Retrieval Scores (JSON)
BM25 score snapshot for comparing neural rerankers against a lexical baseline.
- File
- JSON · Ranking
- Use case
- Model evaluation / JSON parsing
Evaluation & metrics fixtures
Benchmark results, confusion matrices, ROC curves, and classification reports in CSV and JSON, for testing eval dashboards, metric parsers, and leaderboard importers.
Each card starts with one representative test file. Choose a use case, search, or filter to find a specific profile; a card’s variant menu contains its related samples.
More filters and sorting
Results
25 test families · 40 available files · Page 1 of 2
Vision
Caption Eval References (JSON)
Multiple reference captions per image for BLEU/CIDEr caption eval.
- File
- JSON · Vision
- Use case
- Model evaluation
Eval
Classification Report (JSON)
A per-class classification report in the scikit-learn structure: precision, recall, F1, and support for each class plus accuracy and macro/weighted averages. A fixture for testing metric parsers and report renderers.
- File
- JSON · Eval
- Use case
- Model evaluation / JSON parsing
Eval
Confusion Matrix: 3 Classes (CSV)
3×3 confusion matrix CSV for classification metric calculators.
- File
- CSV · Eval
- Use case
- Model evaluation / CSV parsing
Eval
Confusion Matrix: 3-class (CSV)
A 3-class confusion matrix as CSV: rows are the true class, columns the predicted class, cells the counts. Paired with a JSON twin for testing metric parsers and evaluation visualisers.
- File
- CSV · Eval
- Use case
- Model evaluation / CSV parsing
Eval
Confusion Matrix: 5 Classes (CSV)
5×5 confusion matrix with off-diagonal noise for multi-class eval.
- File
- CSV · Eval
- Use case
- Model evaluation
Embeddings
Cosine Similarity Pairs (JSONL)
Precomputed cosine similarity pairs for embedding eval scripts.
- File
- JSONL · Embeddings · 6 records
- Use case
- Model evaluation
Eval
Detection Eval Metrics (JSON)
Synthetic mAP evaluation summary for object-detection benchmark harness tests.
- File
- JSON · Eval
- Use case
- Model evaluation / JSON parsing
Embeddings
Embedding Similarity Matrix (JSON)
Tiny 2×2 cosine similarity matrix for embedding eval unit tests.
- File
- JSON · Embeddings
- Use case
- Model evaluation
Eval
Eval Metric: Accuracy Mini
Minimal SAMPLE eval metric JSON (accuracy) for dashboard parsers.
- File
- JSON · Eval
- Use case
- Model evaluation / JSON parsing
Eval
Model Benchmark Results (JSON)
A model-evaluation summary in JSON, per-task scores for a fictional model across sentiment, NER, summarization, translation, and QA, each with its metric and sample size. A fixture for testing eval dashboards and leaderb
- File
- JSON · Eval
- Use case
- Model evaluation / JSON parsing
Ranking
MRR Eval Ground Truth (JSON)
Mean reciprocal rank ground truth for search eval harness tests.
- File
- JSON · Ranking
- Use case
- Model evaluation
Ranking
nDCG Ground Truth (JSON)
Precomputed DCG/nDCG values for ranking metric unit tests.
- File
- JSON · Ranking
- Use case
- Model evaluation
Model Inference
ONNX Inference Contract - Affine MatMul plus Add Input
The named float32 input tensor payload for the Affine MatMul plus Add model, with explicit shapes and JSON values for runner-independent test setup.
- File
- JSON · Model Inference
- Use case
- Model inference testing / Model evaluation
Model Inference
ONNX Inference Contract - Dynamic-Batch ReduceSum Input
The named float32 input tensor payload for the Dynamic-Batch ReduceSum model, with explicit shapes and JSON values for runner-independent test setup.
- File
- JSON · Model Inference
- Use case
- Model inference testing / Model evaluation
Model Inference
ONNX Inference Contract - Static Identity Input
The named float32 input tensor payload for the Static Identity model, with explicit shapes and JSON values for runner-independent test setup.
- File
- JSON · Model Inference
- Use case
- Model inference testing / Model evaluation
Model Inference
ONNX Inference Contract - Two-Input Broadcast Add Expected Output
The reference-evaluator output for the Two-Input Broadcast Add model and supplied input, including shape, dtype, exact values and a 1e-6 tolerance.
- File
- JSON · Model Inference
- Use case
- Model inference testing / Model evaluation
Eval
Per-class Metrics (JSON)
Per-class precision/recall/F1 snapshot for classification dashboards.
- File
- JSON · Eval
- Use case
- Model evaluation