# Close-ended Spoken Question Answering on Audio-MLQA Source: [Close-ended Spoken Question Answering on Audio-MLQA]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:30:42.559Z Evaluation of model performance on the Audio-MLQA dataset for Close-ended Spoken Question Answering, reporting scores across multiple languages (English, Vietnamese, Spanish, German, Chinese) and overall average. 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 | Close-ended Spoken Question Answering | | Dataset (including any stated split) | Audio-MLQA | | Metric | Score (EN) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Score (EN)](): Higher is better; unit: SCALAR. - [Score (VI)](): Higher is better; unit: SCALAR. - [Score (ES)](): Higher is better; unit: SCALAR. - [Score (DE)](): Higher is better; unit: SCALAR. - [Score (ZH)](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Score (EN) | Result date | Report paper | | --- | --- | --- | --- | | SEA-LION-v3-8B-IT | 4.34 | Not recorded | 69afa5662d603e6de3e43875 | | Whisper-v3 + SEA-LION-v3-8B-IT | 4.2 | Not recorded | 69afa5662d603e6de3e43875 | | Ours (hard-gating) | 4.16 | Not recorded | 69afa5662d603e6de3e43875 | | EN-DiVA | 4.12 | Not recorded | 69afa5662d603e6de3e43875 | | Ours (soft-gating) | 4.12 | Not recorded | 69afa5662d603e6de3e43875 | | ML-DiVA | 4.09 | Not recorded | 69afa5662d603e6de3e43875 | | SeaLLMs-Audio | 3.74 | Not recorded | 69afa5662d603e6de3e43875 | | Qwen2-Audio | 3.54 | Not recorded | 69afa5662d603e6de3e43875 | | Glm-4-voice | 3.04 | Not recorded | 69afa5662d603e6de3e43875 | | MERaLiON-2-10B | 1.73 | Not recorded | 69afa5662d603e6de3e43875 | ### SEA-LION-v3-8B-IT Score (EN): 4.34. Result ID: 69afd6656dbb7075b9582b27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Text-only reference"}. This record does not assert independent reproduction. ### Whisper-v3 + SEA-LION-v3-8B-IT Score (EN): 4.2. Result ID: 69afd6656dbb7075b9582b28. [Reporting paper]() Recorded evaluation configuration: {"Approach category":"Cascaded"}. This record does not assert independent reproduction. ### Ours (hard-gating) Score (EN): 4.16. Result ID: 69afd6656dbb7075b9582b30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Distilled end-to-end","Gating strategy":"hard-gating"}. This record does not assert independent reproduction. ### EN-DiVA Score (EN): 4.12. Result ID: 69afd6656dbb7075b9582b2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Distilled end-to-end","Training protocol":"re-trained baseline"}. This record does not assert independent reproduction. ### Ours (soft-gating) Score (EN): 4.12. Result ID: 69afd6656dbb7075b9582b2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Distilled end-to-end","Gating strategy":"soft-gating"}. This record does not assert independent reproduction. ### ML-DiVA Score (EN): 4.09. Result ID: 69afd6656dbb7075b9582b2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Distilled end-to-end","Training protocol":"re-trained baseline"}. This record does not assert independent reproduction. ### SeaLLMs-Audio Score (EN): 3.74. Result ID: 69afd6656dbb7075b9582b2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Zero-shot end-to-end"}. This record does not assert independent reproduction. ### Qwen2-Audio Score (EN): 3.54. Result ID: 69afd6656dbb7075b9582b2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Zero-shot end-to-end"}. This record does not assert independent reproduction. ### Glm-4-voice Score (EN): 3.04. Result ID: 69afd6656dbb7075b9582b29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach category":"Zero-shot end-to-end"}. This record does not assert independent reproduction. ### MERaLiON-2-10B Score (EN): 1.73. Result ID: 69afd6656dbb7075b9582b2a. [Reporting paper]() Recorded evaluation configuration: {"Approach category":"Zero-shot end-to-end"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.