35 correct out of 45 actual negatives
tp = 50fp = 10fn = 5tn = 35
Result: Specificity 0.7778 · False positive rate 0.2222
Specificity Calculator
Specificity answers "of all the negative cases, how many did the model correctly say were negative?" It is TN ÷ (TN + FP) — the flip side of recall, which looks at positives. High specificity means few false alarms on the negative class.
Enter your values and press Calculate — the result appears here.
Worked examples
No false alarms on negatives
tp = 30fp = 0fn = 20tn = 50
Result: Specificity 1.00
Frequently asked questions
What does specificity tell me?
Specificity is the true negative rate: of the cases that were actually negative, the fraction the model correctly ruled out. High specificity means the model rarely cries wolf.
How do specificity and recall differ?
Recall looks at the positive class (how many actual positives were found); specificity looks at the negative class (how many actual negatives were correctly identified). A test can be highly sensitive but not specific, or vice versa.
What is the false positive rate?
1 − specificity: the share of actual negatives that were wrongly flagged as positive. It is the x-axis of the ROC curve that ROC-AUC summarizes.
📚 Learn More
AI & Machine Learning
Why "Looks Good" Is Never Enough
Key Takeaway --> 🎯 Key Takeaway Evaluating a RAG system requires measuring retrieval quality, ans…
AI & Machine LearningWhat Is Numerical Precision?
Quantization reduces model size by using lower-precision numbers (4-bit instead of 32-bit). A 7B mo…
CybersecurityWhat Is llama.cpp?
llama.cpp is a plain C/C++ inference engine that runs LLMs on CPU without any dependencies. It is t…
CybersecurityWhat Is Local AI?
Local AI means running AI models on your own computer — no internet, no API costs, no data leaving …
AI & Machine LearningThe 7-Step Debugging Process
Debugging an AI agent means tracing through 7 stages: Prompt → Context → Tool Selection → Tool Exec…
AI & Machine LearningThe 8 Dimensions of AI Evaluation
Evaluating an AI system requires more than checking if the answer "looks right." You need 8 dimensi…
🔧 Related Tools
Sensitivity Calculator
Compute sensitivity (recall) — the share of actual positives correctly detected by a test or model.
Try it now →Recall Calculator
Compute recall (sensitivity) — the share of actual positives the model managed to find.
Try it now →ROC-AUC Calculator
Compute the area under the ROC curve from a list of model scores and binary labels (0/1).
Try it now →Accuracy Calculator
Calculate classification accuracy from true/false positives and negatives.
Try it now →💬 Discuss on BestWordz Community
Join the conversation about Machine Learning, specificity, specificity calculator on the BestWordz Community forum.
Visit Forum →💬 Discuss Specificity Calculator
Have questions about Specificity Calculator? Join the BestWordz Community.
Copied!