# Tool Retrieval on publicMCP EN v1.0 (test) Source: [Tool Retrieval on publicMCP EN v1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-29T08:23:01.217Z Evaluation of model performance on Tool Retrieval using the test split of the publicMCP EN v1.0 dataset, measured using Hit Rate (HR), Recall, and Precision percentages. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Tool Retrieval | | Dataset (including any stated split) | publicMCP EN v1.0 (test) | | Metric | Hit Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Hit Rate](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hit Rate | Result date | Report paper | | --- | --- | --- | --- | | A2X | 100 | Not recorded | 6a191dacdbd7150506f8290d | | MiniLM | 80 | Not recorded | 6a191dacdbd7150506f8290d | | MiniLM | 72 | Not recorded | 6a191dacdbd7150506f8290d | | BGE-large-en | 70 | Not recorded | 6a191dacdbd7150506f8290d | | BGE-M3 | 70 | Not recorded | 6a191dacdbd7150506f8290d | | BGE-M3 | 66 | Not recorded | 6a191dacdbd7150506f8290d | | BGE-large-en | 60 | Not recorded | 6a191dacdbd7150506f8290d | | MCP-Zero | 54 | Not recorded | 6a191dacdbd7150506f8290d | | MCP-Zero | 52 | Not recorded | 6a191dacdbd7150506f8290d | ### A2X Hit Rate: 100. Result ID: 6a194be4fbc373592c1394ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K":"-"}. This record does not assert independent reproduction. ### MiniLM Hit Rate: 80. Result ID: 6a194be4fbc373592c1394c3. [Reporting paper]() Recorded evaluation configuration: {"K":"10"}. This record does not assert independent reproduction. ### MiniLM Hit Rate: 72. Result ID: 6a194be4fbc373592c1394c2. [Reporting paper]() Recorded evaluation configuration: {"K":"5"}. This record does not assert independent reproduction. ### BGE-large-en Hit Rate: 70. Result ID: 6a194be4fbc373592c1394c5. [Reporting paper]() Recorded evaluation configuration: {"K":"10"}. This record does not assert independent reproduction. ### BGE-M3 Hit Rate: 70. Result ID: 6a194be4fbc373592c1394c7. [Reporting paper]() Recorded evaluation configuration: {"K":"10"}. This record does not assert independent reproduction. ### BGE-M3 Hit Rate: 66. Result ID: 6a194be4fbc373592c1394c6. [Reporting paper]() Recorded evaluation configuration: {"K":"5"}. This record does not assert independent reproduction. ### BGE-large-en Hit Rate: 60. Result ID: 6a194be4fbc373592c1394c4. [Reporting paper]() Recorded evaluation configuration: {"K":"5"}. This record does not assert independent reproduction. ### MCP-Zero Hit Rate: 54. Result ID: 6a194be4fbc373592c1394c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K":"5"}. This record does not assert independent reproduction. ### MCP-Zero Hit Rate: 52. Result ID: 6a194be4fbc373592c1394c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K":"10"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.