# Context-aware turn-taking on Friends Source: [Context-aware turn-taking on Friends]() Collection index: [llms.txt]() Data updated: 2026-03-13T07:48:16.761Z Evaluation of model performance on context-aware turn-taking using the Friends dataset, reporting metrics including I1, I2, S1, S2, Accuracy, F1avg, and Balanced Accuracy. 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 | Context-aware turn-taking | | Dataset (including any stated split) | Friends | | Metric | I1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [I1](): Higher is better; unit: PERCENT. - [I2](): Higher is better; unit: PERCENT. - [S1](): Higher is better; unit: PERCENT. - [S2](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score (Avg)](): Higher is better; unit: PERCENT. - [Balanced Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | I1 | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-4b-instruct | 100 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-4b-instruct | 100 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-8b | 100 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-8b | 100 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-oss-20b | 98.06 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-oss-20b | 98.06 | Not recorded | 69b399e80636e5bf4afbc8d6 | | LLaMA3.1-8b-instruct | 97.09 | Not recorded | 69b399e80636e5bf4afbc8d6 | | LLaMA3.1-8b-instruct | 97.09 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-5.2 | 94.17 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-5.2 | 94.17 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen2.5-7b | 92.23 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen2.5-7b | 92.23 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Mistral-7b-instruct | 89.32 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Mistral-7b-instruct | 89.32 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gemini-3.1-pro | 82.52 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gemini-3.1-pro | 82.52 | Not recorded | 69b399e80636e5bf4afbc8d6 | ### Qwen3-4b-instruct I1: 100. Result ID: 69b3c0d547f34ce9249d7f0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### Qwen3-4b-instruct I1: 100. Result ID: 69b3c0d547f34ce9249d7f0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### Qwen3-8b I1: 100. Result ID: 69b3c0d547f34ce9249d7f10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### Qwen3-8b I1: 100. Result ID: 69b3c0d547f34ce9249d7f11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### gpt-oss-20b I1: 98.06. Result ID: 69b3c0d547f34ce9249d7f06. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### gpt-oss-20b I1: 98.06. Result ID: 69b3c0d547f34ce9249d7f07. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### LLaMA3.1-8b-instruct I1: 97.09. Result ID: 69b3c0d547f34ce9249d7f08. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### LLaMA3.1-8b-instruct I1: 97.09. Result ID: 69b3c0d547f34ce9249d7f09. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### gpt-5.2 I1: 94.17. Result ID: 69b3c0d547f34ce9249d7f04. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### gpt-5.2 I1: 94.17. Result ID: 69b3c0d547f34ce9249d7f05. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### Qwen2.5-7b I1: 92.23. Result ID: 69b3c0d547f34ce9249d7f0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### Qwen2.5-7b I1: 92.23. Result ID: 69b3c0d547f34ce9249d7f0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### Mistral-7b-instruct I1: 89.32. Result ID: 69b3c0d547f34ce9249d7f0a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### Mistral-7b-instruct I1: 89.32. Result ID: 69b3c0d547f34ce9249d7f0b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### gemini-3.1-pro I1: 82.52. Result ID: 69b3c0d547f34ce9249d7f02. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### gemini-3.1-pro I1: 82.52. Result ID: 69b3c0d547f34ce9249d7f03. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.