# Persona Adherence Alignment on PersonaChat 1.0 (test) Source: [Persona Adherence Alignment on PersonaChat 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-04T20:25:10.563Z Evaluation of dialogue response generation quality on the test split of PersonaChat version 1.0, specifically focusing on Persona Adherence Alignment using similarity and offset metrics. 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 Adherence Alignment | | Dataset (including any stated split) | PersonaChat 1.0 (test) | | Metric | Similarity | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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](): Higher is better; unit: PERCENT. - [Persona Offset](): Lower is better; unit: PERCENT. ## Recorded results | Method | Similarity | Result date | Report paper | | --- | --- | --- | --- | | PersonaChat | 100 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Gemma 3 12B | 98.3 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Qwen3 30B | 97.4 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Gemma 3 27B | 97 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Gemma 3 4B | 94.8 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Qwen3 14B | 91.9 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Gemma 3 1B | 91.8 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Qwen3 4B | 91.2 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | Qwen3 1.7B | 84 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | SPC-New | 83.7 | Not recorded | 69a7bc7e2d603e6de3e3d47d | | SPC | 81.1 | Not recorded | 69a7bc7e2d603e6de3e3d47d | ### PersonaChat Similarity: 100. Result ID: 69a895226dbb7075b9514fe4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Gemma 3 12B Similarity: 98.3. Result ID: 69a895226dbb7075b9514fe5. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Qwen3 30B Similarity: 97.4. Result ID: 69a895226dbb7075b9514fe6. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Gemma 3 27B Similarity: 97. Result ID: 69a895226dbb7075b9514fe7. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Gemma 3 4B Similarity: 94.8. Result ID: 69a895226dbb7075b9514fe8. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Qwen3 14B Similarity: 91.9. Result ID: 69a895226dbb7075b9514fea. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Gemma 3 1B Similarity: 91.8. Result ID: 69a895226dbb7075b9514fe9. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Qwen3 4B Similarity: 91.2. Result ID: 69a895226dbb7075b9514feb. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### Qwen3 1.7B Similarity: 84. Result ID: 69a895226dbb7075b9514fec. [Reporting paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### SPC-New Similarity: 83.7. Result ID: 69a895226dbb7075b9514fed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. ### SPC Similarity: 81.1. Result ID: 69a895226dbb7075b9514fee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Alpha (α) configuration":"1.0","Target-speaker configuration":"target-speaker only"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.