# Audio Question Answering on AudioSet En Source: [Audio Question Answering on AudioSet En]() Collection index: [llms.txt]() Data updated: 2026-03-26T13:58:42.868Z Evaluation of model performance on the AudioSet En dataset for Audio Question Answering tasks. 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 | Audio Question Answering | | Dataset (including any stated split) | AudioSet En | | Metric | Audio QA Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Audio QA Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Audio QA Score | Result date | Report paper | | --- | --- | --- | --- | | GLM-4-Voice | 44.87 | Not recorded | 68fa7b971e209131cea89546 | | VITA-Audio | 40.2 | Not recorded | 68fa7b971e209131cea89546 | | LLaMA-Omni | 39.59 | Not recorded | 68fa7b971e209131cea89546 | | Pretrain+TtT | 26.73 | Not recorded | 68fa7b971e209131cea89546 | | Moshi | 25.63 | Not recorded | 68fa7b971e209131cea89546 | | Kimi-Audio | 19.49 | Not recorded | 68fa7b971e209131cea89546 | | SLAM-Omni | 17.47 | Not recorded | 68fa7b971e209131cea89546 | | TtT | 17.46 | Not recorded | 68fa7b971e209131cea89546 | | Mini-Omni | 15.73 | Not recorded | 68fa7b971e209131cea89546 | | Qwen2.5-3B (AR) | 14.42 | Not recorded | 68fa7b971e209131cea89546 | | Qwen2.5-3B (NAR) | 11.31 | Not recorded | 68fa7b971e209131cea89546 | | SpeechGPT | 10 | Not recorded | 68fa7b971e209131cea89546 | ### GLM-4-Voice Audio QA Score: 44.87. Result ID: 69c53b7847f34ce924aefa1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction. ### VITA-Audio Audio QA Score: 40.2. Result ID: 69c53b7847f34ce924aefa1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### LLaMA-Omni Audio QA Score: 39.59. Result ID: 69c53b7847f34ce924aefa1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### Pretrain+TtT Audio QA Score: 26.73. Result ID: 69c53b7847f34ce924aefa25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B"}. This record does not assert independent reproduction. ### Moshi Audio QA Score: 25.63. Result ID: 69c53b7847f34ce924aefa1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Kimi-Audio Audio QA Score: 19.49. Result ID: 69c53b7847f34ce924aefa1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### SLAM-Omni Audio QA Score: 17.47. Result ID: 69c53b7847f34ce924aefa21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"0.5B"}. This record does not assert independent reproduction. ### TtT Audio QA Score: 17.46. Result ID: 69c53b7847f34ce924aefa24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B"}. This record does not assert independent reproduction. ### Mini-Omni Audio QA Score: 15.73. Result ID: 69c53b7847f34ce924aefa20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"0.5B"}. This record does not assert independent reproduction. ### Qwen2.5-3B (AR) Audio QA Score: 14.42. Result ID: 69c53b7847f34ce924aefa22. [Reporting paper]() Recorded evaluation configuration: {"Size":"3B"}. This record does not assert independent reproduction. ### Qwen2.5-3B (NAR) Audio QA Score: 11.31. Result ID: 69c53b7847f34ce924aefa23. [Reporting paper]() Recorded evaluation configuration: {"Size":"3B"}. This record does not assert independent reproduction. ### SpeechGPT Audio QA Score: 10. Result ID: 69c53b7847f34ce924aefa1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.