# Social Reasoning on Sotopia (all) Source: [Social Reasoning on Sotopia (all)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:30:53.471Z Evaluation of model performance on Social Reasoning tasks using the Sotopia (all) dataset, measured by Rel, Know, Goal, and Avg. scores. 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 | Social Reasoning | | Dataset (including any stated split) | Sotopia (all) | | Metric | Rel Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Rel Score](): Higher is better; unit: SCALAR. - [Know Score](): Higher is better; unit: SCALAR. - [Goal Score](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Rel Score | Result date | Report paper | | --- | --- | --- | --- | | FT+MS | 2.73 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+MS+Uttr (TOMA) | 2.7 | Not recorded | 68fa7ba61e209131cea89a30 | | Base+MS | 2.47 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+Uttr | 2.42 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+MS | 2.37 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+MS+Uttr (TOMA) | 2.37 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+MS+Uttr (TOMA) | 2.18 | Not recorded | 68fa7ba61e209131cea89a30 | | Base | 2.07 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+Uttr | 1.92 | Not recorded | 68fa7ba61e209131cea89a30 | | Base+MS | 1.54 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+MS | 1.49 | Not recorded | 68fa7ba61e209131cea89a30 | | FT+Uttr | 1.28 | Not recorded | 68fa7ba61e209131cea89a30 | | Base+MS | 1.2 | Not recorded | 68fa7ba61e209131cea89a30 | | Base | 0.97 | Not recorded | 68fa7ba61e209131cea89a30 | | Base | 0.27 | Not recorded | 68fa7ba61e209131cea89a30 | ### FT+MS Rel Score: 2.73. Result ID: 69ddfa1247f34ce924c55e92. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT+MS+Uttr (TOMA) Rel Score: 2.7. Result ID: 69ddfa1247f34ce924c55e93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Base+MS Rel Score: 2.47. Result ID: 69ddfa1247f34ce924c55e90. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT+Uttr Rel Score: 2.42. Result ID: 69ddfa1247f34ce924c55e91. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT+MS Rel Score: 2.37. Result ID: 69ddfa1247f34ce924c55e8d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction. ### FT+MS+Uttr (TOMA) Rel Score: 2.37. Result ID: 69ddfa1247f34ce924c55e98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B"}. This record does not assert independent reproduction. ### FT+MS+Uttr (TOMA) Rel Score: 2.18. Result ID: 69ddfa1247f34ce924c55e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction. ### Base Rel Score: 2.07. Result ID: 69ddfa1247f34ce924c55e8f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT+Uttr Rel Score: 1.92. Result ID: 69ddfa1247f34ce924c55e8c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction. ### Base+MS Rel Score: 1.54. Result ID: 69ddfa1247f34ce924c55e8b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction. ### FT+MS Rel Score: 1.49. Result ID: 69ddfa1247f34ce924c55e97. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B"}. This record does not assert independent reproduction. ### FT+Uttr Rel Score: 1.28. Result ID: 69ddfa1247f34ce924c55e96. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B"}. This record does not assert independent reproduction. ### Base+MS Rel Score: 1.2. Result ID: 69ddfa1247f34ce924c55e95. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B"}. This record does not assert independent reproduction. ### Base Rel Score: 0.97. Result ID: 69ddfa1247f34ce924c55e8a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction. ### Base Rel Score: 0.27. Result ID: 69ddfa1247f34ce924c55e94. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.