# Non-Verbal (NV) Type Prediction on Affectron NV Prediction (test) Source: [Non-Verbal (NV) Type Prediction on Affectron NV Prediction (test)]() Collection index: [llms.txt]() Data updated: 2026-03-17T10:14:44.546Z Evaluation of Non-Verbal (NV) Type Prediction performance on the test split of the Affectron NV Prediction dataset, measured using Acc@1/3/5, JSD, and HD 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 | Non-Verbal (NV) Type Prediction | | Dataset (including any stated split) | Affectron NV Prediction (test) | | Metric | Acc@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Acc@1](): Higher is better; unit: PERCENT. - [Acc@3](): Higher is better; unit: PERCENT. - [Acc@5](): Higher is better; unit: PERCENT. - [JSD](): Lower is better; unit: SCALAR. - [HD](): Lower is better; unit: SCALAR. ## Recorded results | Method | Acc@1 | Result date | Report paper | | --- | --- | --- | --- | | Affectron | 75.77 | Not recorded | 69b8e0180636e5bf4afbeaed | | Qwen2.5-Omni-7B | 20.07 | Not recorded | 69b8e0180636e5bf4afbeaed | | Qwen2-Audio-7B | 12.83 | Not recorded | 69b8e0180636e5bf4afbeaed | | Qwen2.5-Omni-7B | 12.47 | Not recorded | 69b8e0180636e5bf4afbeaed | | Qwen2-Audio-7B | 12 | Not recorded | 69b8e0180636e5bf4afbeaed | ### Affectron Acc@1: 75.77. Result ID: 69b9298347f34ce924a26c61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text and Speech","Zero-shot":"true","Model Scale":"330M"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B Acc@1: 20.07. Result ID: 69b9298347f34ce924a26c60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text and Speech","Zero-shot":"true","Model Scale":"7B"}. This record does not assert independent reproduction. ### Qwen2-Audio-7B Acc@1: 12.83. Result ID: 69b9298347f34ce924a26c5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text and Speech","Zero-shot":"true","Model Scale":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B Acc@1: 12.47. Result ID: 69b9298347f34ce924a26c5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text only","Zero-shot":"true","Model Scale":"7B"}. This record does not assert independent reproduction. ### Qwen2-Audio-7B Acc@1: 12. Result ID: 69b9298347f34ce924a26c5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text only","Zero-shot":"true","Model Scale":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.