AI Model Performance
Structured results of the current TennisFlow models on the internal validation dataset.
Current results
| Task | Metric | Result |
|---|---|---|
| Stroke Detection | Precision | 98.8 % |
| Stroke Detection | Recall | 97.9 % |
| Stroke Detection | F1 Score | 98.4 % |
| Stroke Type Classification | Accuracy | 99.83 % |
| Stroke Detail Classification | Accuracy | 95.7 % |
Show earlier results
Results from August 5, 2026
| Task | Metric | Result |
|---|---|---|
| Stroke Detection | Precision | 97.66 % |
| Stroke Detection | Recall | 97.73 % |
| Stroke Detection | F1 Score | 97.70 % |
| Stroke Type Classification | Accuracy | 99.9 % |
| Stroke Detail Classification | Accuracy | 95.9 % |
The results are measured on TennisFlow’s internal validation dataset using manually annotated ground-truth data.
Why do we publish our AI metrics?
Many apps promote “AI” without making its quality measurable. At TennisFlow, we want to be transparent. That is why we regularly publish the performance data of our AI models and document their progress with every release.