# Music Classification on Surge Source: [Music Classification on Surge]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:35.111Z Evaluation of music classification performance using the Surge dataset, typically measured by 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 | Music Classification | | Dataset (including any stated split) | Surge | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 29 of 29 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MSM-MAE | 42.5 | Not recorded | 68fa6ea91e209131cea4130f | | M2D-CLAP stage1 2024 | 42.4 | Not recorded | 68fa80771e209131cea9d2fc | | M2D-CLAP stage1 2025 | 42.2 | Not recorded | 68fa80771e209131cea9d2fc | | M2D | 42.1 | Not recorded | 68fa80771e209131cea9d2fc | | M2D | 42.1 | Not recorded | 68fa72cf1e209131cea58a6c | | M2D | 41.8 | Not recorded | 68fa6ea91e209131cea4130f | | M2D-AS | 41.7 | Not recorded | 68fa72cf1e209131cea58a6c | | M2D-CLAP2025 | 41.1 | Not recorded | 68fa80771e209131cea9d2fc | | M2D | 41 | Not recorded | 68fa6ea91e209131cea4130f | | ATST-Frame | 40.6 | Not recorded | 68fa80771e209131cea9d2fc | | M2DAS | 40.5 | Not recorded | 68fa80771e209131cea9d2fc | | BEATsiter3 | 39.3 | Not recorded | 68fa80771e209131cea9d2fc | | CED | 38.9 | Not recorded | 68fa80771e209131cea9d2fc | | ATST Base | 37.7 | Not recorded | 68fa6ea91e209131cea4130f | | BYOL-A | 37.6 | Not recorded | 68fa6ea91e209131cea4130f | | BEATsiter3+ | 35.7 | Not recorded | 68fa80771e209131cea9d2fc | | BEATSiter3+ | 35.7 | Not recorded | 68fa72cf1e209131cea58a6c | | AST-Fusion#5#12 | 34.6 | Not recorded | 68fa6ea91e209131cea4130f | | ATST-Clip | 32.8 | Not recorded | 68fa80771e209131cea9d2fc | | CLAP2023 | 27.2 | Not recorded | 68fa80771e209131cea9d2fc | | HTS-AT | 26.3 | Not recorded | 68fa80771e209131cea9d2fc | | HTS-AT | 26.3 | Not recorded | 68fa72cf1e209131cea58a6c | | AST | 25.8 | Not recorded | 68fa72cf1e209131cea58a6c | | AST | 25.7 | Not recorded | 68fa80771e209131cea9d2fc | | WavCaps | 21.1 | Not recorded | 68fa80771e209131cea9d2fc | | Wav2Vec2 | 15.2 | Not recorded | 68fa6ea91e209131cea4130f | | LAION-CLAP | 14.8 | Not recorded | 68fa80771e209131cea9d2fc | | PANNs CNN14 | 10.9 | Not recorded | 68fa80771e209131cea9d2fc | | CLAP2022 | 8.4 | Not recorded | 68fa80771e209131cea9d2fc | ### MSM-MAE Accuracy: 42.5. Result ID: 69904ae03a6c314849ff840b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### M2D-CLAP stage1 2024 Accuracy: 42.4. Result ID: 698b96547a967eddb76fd537. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### M2D-CLAP stage1 2025 Accuracy: 42.2. Result ID: 698b96547a967eddb76fd536. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### M2D Accuracy: 42.1. Result ID: 698b96547a967eddb76fd533. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### M2D Accuracy: 42.1. Result ID: 69927d653a6c3148490f4eb5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"86M","Masking ratio":"0.7","Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### M2D Accuracy: 41.8. Result ID: 69904ae03a6c314849ff840d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation","Masking ratio":"0.7"}. This record does not assert independent reproduction. ### M2D-AS Accuracy: 41.7. Result ID: 69927d653a6c3148490f4eb4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"86M","Masking ratio":"0.7","Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### M2D-CLAP2025 Accuracy: 41.1. Result ID: 698b96547a967eddb76fd535. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### M2D Accuracy: 41. Result ID: 69904ae03a6c314849ff840c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation","Masking ratio":"0.6"}. This record does not assert independent reproduction. ### ATST-Frame Accuracy: 40.6. Result ID: 698b96547a967eddb76fd528. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### M2DAS Accuracy: 40.5. Result ID: 698b96547a967eddb76fd534. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### BEATsiter3 Accuracy: 39.3. Result ID: 698b96547a967eddb76fd529. [Reporting paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### CED Accuracy: 38.9. Result ID: 698b96547a967eddb76fd52b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### ATST Base Accuracy: 37.7. Result ID: 69904ae03a6c314849ff840a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation","Variant":"Base"}. This record does not assert independent reproduction. ### BYOL-A Accuracy: 37.6. Result ID: 69904ae03a6c314849ff8409. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### BEATsiter3+ Accuracy: 35.7. Result ID: 698b96547a967eddb76fd52a. [Reporting paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### BEATSiter3+ Accuracy: 35.7. Result ID: 69927d653a6c3148490f4eb3. [Reporting paper]() Recorded evaluation configuration: {"# Params":"90M","Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### AST-Fusion#5#12 Accuracy: 34.6. Result ID: 69904ae03a6c314849ff840e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation","Variant":"#5#12"}. This record does not assert independent reproduction. ### ATST-Clip Accuracy: 32.8. Result ID: 698b96547a967eddb76fd527. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":false}. This record does not assert independent reproduction. ### CLAP2023 Accuracy: 27.2. Result ID: 698b96547a967eddb76fd531. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### HTS-AT Accuracy: 26.3. Result ID: 698b96547a967eddb76fd52d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### HTS-AT Accuracy: 26.3. Result ID: 69927d653a6c3148490f4eb2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"31M","Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### AST Accuracy: 25.8. Result ID: 69927d653a6c3148490f4eb1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"86M","Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### AST Accuracy: 25.7. Result ID: 698b96547a967eddb76fd52c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### WavCaps Accuracy: 21.1. Result ID: 698b96547a967eddb76fd532. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### Wav2Vec2 Accuracy: 15.2. Result ID: 69904ae03a6c314849ff8408. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### LAION-CLAP Accuracy: 14.8. Result ID: 698b96547a967eddb76fd52f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### PANNs CNN14 Accuracy: 10.9. Result ID: 698b96547a967eddb76fd52e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. ### CLAP2022 Accuracy: 8.4. Result ID: 698b96547a967eddb76fd530. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Audio enc. fine-tuning on AudioSet":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.