# Alignment Detection on AnyAudio-Judge English Source: [Alignment Detection on AnyAudio-Judge English]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:00:27.808Z Evaluation of model performance on the AnyAudio-Judge English dataset, assessing Alignment Detection capabilities across Speech, Sound, and Music modalities for both real and generated inputs. 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 | Alignment Detection | | Dataset (including any stated split) | AnyAudio-Judge English | | Metric | Accuracy (Speech, Real) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 (Speech, Real)](): Higher is better; unit: PERCENT. - [Accuracy (Speech, Generated)](): Higher is better; unit: PERCENT. - [Accuracy (Sound, Real)](): Higher is better; unit: PERCENT. - [Accuracy (Sound, Generated)](): Higher is better; unit: PERCENT. - [Accuracy (Music, Real)](): Higher is better; unit: PERCENT. - [Accuracy (Music, Generated)](): Higher is better; unit: PERCENT. - [Accuracy (Mixed)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Speech, Real) | Result date | Report paper | | --- | --- | --- | --- | | AnyAudio-Judge | 91.42 | Not recorded | 6a21065ac10484bac23efe71 | | Gemini-2.5-Pro | 91.22 | Not recorded | 6a21065ac10484bac23efe71 | | Gemini-2.5-Pro | 89 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen3-Omni-30B-A3B-Instruct | 88.92 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen3-Omni-30B-A3B-Captioner | 88.5 | Not recorded | 6a21065ac10484bac23efe71 | | Kimi-Audio-7B-Instruct | 80.08 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen2.5-Omni-7B | 77.25 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen3-Omni-30B-A3B-Captioner | 70.46 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen3-Omni-30B-A3B-Instruct | 65.42 | Not recorded | 6a21065ac10484bac23efe71 | | MiDashengLM | 64.92 | Not recorded | 6a21065ac10484bac23efe71 | | Audio-Flamingo3 | 59 | Not recorded | 6a21065ac10484bac23efe71 | | Kimi-Audio-7B-Instruct | 50.25 | Not recorded | 6a21065ac10484bac23efe71 | | Qwen2.5-Omni-7B | 50.25 | Not recorded | 6a21065ac10484bac23efe71 | | Audio-Flamingo3 | 48.87 | Not recorded | 6a21065ac10484bac23efe71 | | MiDashengLM | 48.58 | Not recorded | 6a21065ac10484bac23efe71 | ### AnyAudio-Judge Accuracy (Speech, Real): 91.42. Result ID: 6a213097fbc373592c1c90cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Accuracy (Speech, Real): 91.22. Result ID: 6a213097fbc373592c1c90c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Accuracy (Speech, Real): 89. Result ID: 6a213097fbc373592c1c90ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Qwen3-Omni-30B-A3B-Instruct Accuracy (Speech, Real): 88.92. Result ID: 6a213097fbc373592c1c90c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Qwen3-Omni-30B-A3B-Captioner Accuracy (Speech, Real): 88.5. Result ID: 6a213097fbc373592c1c90c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Kimi-Audio-7B-Instruct Accuracy (Speech, Real): 80.08. Result ID: 6a213097fbc373592c1c90c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B Accuracy (Speech, Real): 77.25. Result ID: 6a213097fbc373592c1c90c4. [Reporting paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Qwen3-Omni-30B-A3B-Captioner Accuracy (Speech, Real): 70.46. Result ID: 6a213097fbc373592c1c90c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### Qwen3-Omni-30B-A3B-Instruct Accuracy (Speech, Real): 65.42. Result ID: 6a213097fbc373592c1c90c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### MiDashengLM Accuracy (Speech, Real): 64.92. Result ID: 6a213097fbc373592c1c90c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Audio-Flamingo3 Accuracy (Speech, Real): 59. Result ID: 6a213097fbc373592c1c90be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"dynamic rubric"}. This record does not assert independent reproduction. ### Kimi-Audio-7B-Instruct Accuracy (Speech, Real): 50.25. Result ID: 6a213097fbc373592c1c90c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B Accuracy (Speech, Real): 50.25. Result ID: 6a213097fbc373592c1c90c3. [Reporting paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### Audio-Flamingo3 Accuracy (Speech, Real): 48.87. Result ID: 6a213097fbc373592c1c90bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. ### MiDashengLM Accuracy (Speech, Real): 48.58. Result ID: 6a213097fbc373592c1c90bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"holistic"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.