# Audio Reasoning (Multiple Choice) on SpeechR MC Source: [Audio Reasoning (Multiple Choice) on SpeechR MC]() Collection index: [llms.txt]() Data updated: 2026-05-21T10:14:39.000Z Evaluation of model performance on the SpeechR MC dataset for Audio Reasoning tasks requiring Multiple Choice answers, 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 | Audio Reasoning (Multiple Choice) | | Dataset (including any stated split) | SpeechR MC | | Metric | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Step-Audio-R1 | 70.5 | Not recorded | 68fa7b251e209131cea86d9e | | VIRBA | 67.4 | Not recorded | 68fa7b251e209131cea86d9e | | AF3 | 64.2 | Not recorded | 68fa7b251e209131cea86d9e | | VIRBA | 62.8 | Not recorded | 68fa7b251e209131cea86d9e | | Kimi-Audio | 61.8 | Not recorded | 68fa7b251e209131cea86d9e | | Qwen2.5-Omni | 57.4 | Not recorded | 68fa7b251e209131cea86d9e | | Single-view RL | 52.7 | Not recorded | 68fa7b251e209131cea86d9e | | GLM-4-Voice | 51 | Not recorded | 68fa7b251e209131cea86d9e | | Qwen2-Audio base | 45.8 | Not recorded | 68fa7b251e209131cea86d9e | ### Step-Audio-R1 Accuracy: 70.5. Result ID: 6a0edadbfbc373592c06a599. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VIRBA Accuracy: 67.4. Result ID: 6a0edadbfbc373592c06a59c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Omni"}. This record does not assert independent reproduction. ### AF3 Accuracy: 64.2. Result ID: 6a0edadbfbc373592c06a598. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Full name":"Audio Flamingo 3"}. This record does not assert independent reproduction. ### VIRBA Accuracy: 62.8. Result ID: 6a0edadbfbc373592c06a59b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2-Audio"}. This record does not assert independent reproduction. ### Kimi-Audio Accuracy: 61.8. Result ID: 6a0edadbfbc373592c06a597. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-Omni Accuracy: 57.4. Result ID: 6a0edadbfbc373592c06a596. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Single-view RL Accuracy: 52.7. Result ID: 6a0edadbfbc373592c06a59a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLM-4-Voice Accuracy: 51. Result ID: 6a0edadbfbc373592c06a595. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-Audio base Accuracy: 45.8. Result ID: 6a0edadbfbc373592c06a594. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.