# Online Search Evaluation on Online Search Traffic 30-day A/B experiment (online) Source: [Online Search Evaluation on Online Search Traffic 30-day A/B experiment (online)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:11:24.935Z Evaluation of model performance on an online search A/B experiment conducted over 30 days, measuring key online metrics such as Click-Through Rate (CTR), User CTR (UCTR), Predicted CTR (PCTR), and overall Search Benefit (ΔGSB). 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 | Online Search Evaluation | | Dataset (including any stated split) | Online Search Traffic 30-day A/B experiment (online) | | Metric | ΔGSB | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | 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 - [ΔGSB](): Higher is better; unit: PERCENT. - [CTR](): Higher is better; unit: PERCENT. - [PCTR](): Higher is better; unit: PERCENT. - [UCTR](): Higher is better; unit: PERCENT. ## Recorded results | Method | ΔGSB | Result date | Report paper | | --- | --- | --- | --- | | EQE | 12.5 | Not recorded | 68fa6f951e209131cea466e7 | ### EQE ΔGSB: 12.5. Result ID: 6990cd8b3a6c3148490365d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.