# Context-aware turn-taking on SPGI Source: [Context-aware turn-taking on SPGI]() Collection index: [llms.txt]() Data updated: 2026-03-13T07:48:16.790Z Evaluation of Context-aware turn-taking performance on the SPGI dataset, using metrics such as 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) | SPGI | | Metric | I1 Score | | 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 Score](): Higher is better; unit: PERCENT. - [I2 Score](): Higher is better; unit: PERCENT. - [S1 Score](): Higher is better; unit: PERCENT. - [S2 Score](): 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 Score | Result date | Report paper | | --- | --- | --- | --- | | LLaMA3.1-8b-instruct | 96.86 | Not recorded | 69b399e80636e5bf4afbc8d6 | | LLaMA3.1-8b-instruct | 96.86 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-4b-instruct | 94.94 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-4b-instruct | 94.94 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-8b | 94.94 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen3-8b | 94.94 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen2.5-7b | 89.28 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Qwen2.5-7b | 89.28 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-5.2 | 85.3 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-5.2 | 85.3 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Mistral-7b-instruct | 84.6 | Not recorded | 69b399e80636e5bf4afbc8d6 | | Mistral-7b-instruct | 84.6 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gemini-3.1-pro | 79.35 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gemini-3.1-pro | 79.35 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-oss-20b | 68.63 | Not recorded | 69b399e80636e5bf4afbc8d6 | | gpt-oss-20b | 68.63 | Not recorded | 69b399e80636e5bf4afbc8d6 | ### LLaMA3.1-8b-instruct I1 Score: 96.86. Result ID: 69b3c0d547f34ce9249d7f18. [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 Score: 96.86. Result ID: 69b3c0d547f34ce9249d7f19. [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. ### Qwen3-4b-instruct I1 Score: 94.94. Result ID: 69b3c0d547f34ce9249d7f1e. [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 Score: 94.94. Result ID: 69b3c0d547f34ce9249d7f1f. [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 Score: 94.94. Result ID: 69b3c0d547f34ce9249d7f20. [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 Score: 94.94. Result ID: 69b3c0d547f34ce9249d7f21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### Qwen2.5-7b I1 Score: 89.28. Result ID: 69b3c0d547f34ce9249d7f1c. [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 Score: 89.28. Result ID: 69b3c0d547f34ce9249d7f1d. [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-5.2 I1 Score: 85.3. Result ID: 69b3c0d547f34ce9249d7f14. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Single"}. This record does not assert independent reproduction. ### gpt-5.2 I1 Score: 85.3. Result ID: 69b3c0d547f34ce9249d7f15. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### Mistral-7b-instruct I1 Score: 84.6. Result ID: 69b3c0d547f34ce9249d7f1a. [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 Score: 84.6. Result ID: 69b3c0d547f34ce9249d7f1b. [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 Score: 79.35. Result ID: 69b3c0d547f34ce9249d7f12. [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 Score: 79.35. Result ID: 69b3c0d547f34ce9249d7f13. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","System Prompt Frequency":"Repeated twice"}. This record does not assert independent reproduction. ### gpt-oss-20b I1 Score: 68.63. Result ID: 69b3c0d547f34ce9249d7f16. [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 Score: 68.63. Result ID: 69b3c0d547f34ce9249d7f17. [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. Page 1 of 1. This is an index page, not the full collection.