Model Evaluation & Metrics Calculators

Turning raw counts into the numbers a model is judged on: precision, recall and F1 from a confusion matrix, and perplexity from cross-entropy loss — including the cases where an impressive-looking score means nothing.

3 calculators in this category

Which one do you need?

F1 Score & Classification Metrics Calculator
Turn a confusion matrix into precision, recall, F1, F-beta, balanced accuracy and the Matthews correlation coefficient, with worked examples.
Confusion Matrix Metrics Calculator
Turn true and false positives and negatives into accuracy, precision, recall, specificity, balanced accuracy, Matthews correlation and Cohen's kappa.
Perplexity Calculator (From Cross-Entropy Loss)
Convert cross-entropy loss to perplexity and bits per token, compare against a uniform vocabulary baseline, and translate token perplexity to word level.

More ai, llm & machine learning engineering categories

Related categories in other subjects

Where this work overlaps other trades and disciplines.