# Out-of-Scope Query Detection on CLINC-Banking (C-Bank) (test) Source: [Out-of-Scope Query Detection on CLINC-Banking (C-Bank) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:25:19.951Z Evaluation of Out-of-Scope Query Detection performance on the test split of the CLINC-Banking dataset, measured using AUC metrics at various thresholds (10%, 25%, 50%, ROC). 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 | Out-of-Scope Query Detection | | Dataset (including any stated split) | CLINC-Banking (C-Bank) (test) | | Metric | AUC (10% Threshold) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [AUC (10% Threshold)](): Higher is better; unit: PERCENT. - [AUC (25% Threshold)](): Higher is better; unit: PERCENT. - [AUC (50% Threshold)](): Higher is better; unit: PERCENT. - [AUC (ROC)](): Higher is better; unit: PERCENT. ## Recorded results | Method | AUC (10% Threshold) | Result date | Report paper | | --- | --- | --- | --- | | ColdFusion | 84.4 | Not recorded | 68fa73601e209131cea5c0a8 | | ZS | 83.1 | Not recorded | 68fa73601e209131cea5c0a8 | | ZS | 82.7 | Not recorded | 68fa73601e209131cea5c0a8 | | ColdFusion | 82.3 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 69.7 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 64.8 | Not recorded | 68fa73601e209131cea5c0a8 | ### ColdFusion AUC (10% Threshold): 84.4. Result ID: 6992d5e33a6c31484911d16a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination (r)":"5%"}. This record does not assert independent reproduction. ### ZS AUC (10% Threshold): 83.1. Result ID: 6992d5e33a6c31484911d165. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination (r)":"5%"}. This record does not assert independent reproduction. ### ZS AUC (10% Threshold): 82.7. Result ID: 6992d5e33a6c31484911d168. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination (r)":"5%"}. This record does not assert independent reproduction. ### ColdFusion AUC (10% Threshold): 82.3. Result ID: 6992d5e33a6c31484911d167. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination (r)":"5%"}. This record does not assert independent reproduction. ### DN2 AUC (10% Threshold): 69.7. Result ID: 6992d5e33a6c31484911d169. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination (r)":"5%"}. This record does not assert independent reproduction. ### DN2 AUC (10% Threshold): 64.8. Result ID: 6992d5e33a6c31484911d166. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination (r)":"5%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.