# Persona Discovery on Gemini Flash (Small Target) 2.5 Source: [Persona Discovery on Gemini Flash (Small Target) 2.5]() Collection index: [llms.txt]() Data updated: 2026-04-28T09:39:52.907Z Evaluation of Persona Discovery capabilities using the Gemini Flash (Small Target) 2.5 dataset, measured by Similarity Score. 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 | Persona Discovery | | Dataset (including any stated split) | Gemini Flash (Small Target) 2.5 | | Metric | Similarity Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Similarity Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Similarity Score | Result date | Report paper | | --- | --- | --- | --- | | PD-Agent | 98 | Not recorded | 69f03f3155a3c32af89fa1fa | | PD-Agent | 92 | Not recorded | 69f03f3155a3c32af89fa1fa | | PD-Agent | 91 | Not recorded | 69f03f3155a3c32af89fa1fa | | PD-Agent | 90 | Not recorded | 69f03f3155a3c32af89fa1fa | | PD-Agent | 89 | Not recorded | 69f03f3155a3c32af89fa1fa | | PD-Agent | 88 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 87 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 86 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 84 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 83 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 83 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 82 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 81 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 80 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 79 | Not recorded | 69f03f3155a3c32af89fa1fa | | Freq-Aware | 78 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 77 | Not recorded | 69f03f3155a3c32af89fa1fa | | Vanilla | 76 | Not recorded | 69f03f3155a3c32af89fa1fa | ### PD-Agent Similarity Score: 98. Result ID: 69f0805547f34ce924d6d121. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"o1-mini (Reasoning)"}. This record does not assert independent reproduction. ### PD-Agent Similarity Score: 92. Result ID: 69f0805547f34ce924d6d118. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek V3"}. This record does not assert independent reproduction. ### PD-Agent Similarity Score: 91. Result ID: 69f0805547f34ce924d6d115. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini 1.5 Pro"}. This record does not assert independent reproduction. ### PD-Agent Similarity Score: 90. Result ID: 69f0805547f34ce924d6d11e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### PD-Agent Similarity Score: 89. Result ID: 69f0805547f34ce924d6d112. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Claude 3.5 Sonnet"}. This record does not assert independent reproduction. ### PD-Agent Similarity Score: 88. Result ID: 69f0805547f34ce924d6d11b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1 70B-Inst."}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 87. Result ID: 69f0805547f34ce924d6d11d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 86. Result ID: 69f0805547f34ce924d6d120. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"o1-mini (Reasoning)"}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 84. Result ID: 69f0805547f34ce924d6d11f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"o1-mini (Reasoning)"}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 83. Result ID: 69f0805547f34ce924d6d113. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini 1.5 Pro"}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 83. Result ID: 69f0805547f34ce924d6d117. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek V3"}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 82. Result ID: 69f0805547f34ce924d6d114. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini 1.5 Pro"}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 81. Result ID: 69f0805547f34ce924d6d116. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek V3"}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 80. Result ID: 69f0805547f34ce924d6d11c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 79. Result ID: 69f0805547f34ce924d6d11a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1 70B-Inst."}. This record does not assert independent reproduction. ### Freq-Aware Similarity Score: 78. Result ID: 69f0805547f34ce924d6d111. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude 3.5 Sonnet"}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 77. Result ID: 69f0805547f34ce924d6d119. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1 70B-Inst."}. This record does not assert independent reproduction. ### Vanilla Similarity Score: 76. Result ID: 69f0805547f34ce924d6d110. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude 3.5 Sonnet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.