# Spoken Language Understanding on SLURP 3 tasks Source: [Spoken Language Understanding on SLURP 3 tasks]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:13.886Z Evaluation of Spoken Language Understanding performance on the SLURP 3 tasks configuration, measured using Average Accuracy, Last Accuracy, and Average WER. 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 | Spoken Language Understanding | | Dataset (including any stated split) | SLURP 3 tasks | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Last Accuracy](): Higher is better; unit: PERCENT. - [Average WER](): Lower is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Offline | 84.41 | Not recorded | 68fa73761e209131cea5cb00 | | COCONUT+S-KD | 75.58 | Not recorded | 68fa73761e209131cea5cb00 | | S-KD | 74.28 | Not recorded | 68fa73761e209131cea5cb00 | | COCONUT | 72.75 | Not recorded | 68fa73761e209131cea5cb00 | | T-KD | 72.44 | Not recorded | 68fa73761e209131cea5cb00 | | A-KD | 72.1 | Not recorded | 68fa73761e209131cea5cb00 | | ER iCaRL | 71.94 | Not recorded | 68fa73761e209131cea5cb00 | | ER rand | 71.44 | Not recorded | 68fa73761e209131cea5cb00 | | Fine-tuning | 46.65 | Not recorded | 68fa73761e209131cea5cb00 | ### Offline Average Accuracy: 84.41. Result ID: 6992ee163a6c3148491271b4. [Reporting paper]() Recorded evaluation configuration: {"continual learning":false}. This record does not assert independent reproduction. ### COCONUT+S-KD Average Accuracy: 75.58. Result ID: 6992ee163a6c3148491271bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### S-KD Average Accuracy: 74.28. Result ID: 6992ee163a6c3148491271ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### COCONUT Average Accuracy: 72.75. Result ID: 6992ee163a6c3148491271bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### T-KD Average Accuracy: 72.44. Result ID: 6992ee163a6c3148491271b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### A-KD Average Accuracy: 72.1. Result ID: 6992ee163a6c3148491271b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### ER iCaRL Average Accuracy: 71.94. Result ID: 6992ee163a6c3148491271b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### ER rand Average Accuracy: 71.44. Result ID: 6992ee163a6c3148491271b6. [Reporting paper]() Recorded evaluation configuration: {"buffer size":"1%"}. This record does not assert independent reproduction. ### Fine-tuning Average Accuracy: 46.65. Result ID: 6992ee163a6c3148491271b5. [Reporting paper]() Recorded evaluation configuration: {"continual learning":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.