List your company

Multimodal Audio Understanding on MMAU mini v05.15.25 (test)

79.6Sound AccuracyAudio Flamingo 3
18.03234.0165065.984Mar 10, 2026

Evaluation results

MethodLinks
Audio Flamingo 3Size=8B, No LLM Modification=×, # Samples=26.7M, # Hours=54.4K2026.0379.67466.473.3
Qwen2.5-OmniSize=7B, No LLM Modification=×, # Tokens=0.3T2026.0378.165.970.671.5
Audio Flamingo 2Size=3B, No LLM Modification=×, # Samples=5.9M2026.0371.57144.762.4
DeSTA-2.5-AudioSize=8B, No LLM Modification=✓, # Samples=5M, # Hours=7K2026.0370.356.371.566
Audio ReasonerSize=8B, No LLM Modification=×, # Samples=> 1.2M, # Hours=> 320K2026.0367.969.266.167.7
Qwen2-Audio-InstructSize=7B, No LLM Modification=×, # Hours=320K2026.0367.356.355.359.6
ALARM-CASize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0366.457.260.161.2
Phi-4-MultimodalSize=4B, No LLM Modification=×, # Samples=> 28M, # Hours=> 2M2026.0365.564.3767.2766.7
GPT-4o Audio2026.0364.656.366.762.5
ALARM-ESize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.036454.877.265.3
AL-SSLAM-RSize=4B, No LLM Modification=✓, # Samples=0.4M, # Hours=1.2K, # Tokens=108M2026.0361.346.745.951.3
ALARM-PSize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0358.652.768.860
Gemma 3nSize=8B4E2026.0355.956.961.358
AL-Whisper-RSize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0352.346.757.152
Gemma 3nSize=6B2E2026.0351.452.152.251.7
GPT-4o mini Audio2026.0350.839.269.153
AL-MuQ-RSize=4B, No LLM Modification=✓, # Samples=0.4M, # Hours=1.5K, # Tokens=137M2026.0350.553.940.8448.4
AL-W2VBERT2-RSize=4B, No LLM Modification=✓, # Samples=0.5M, # Hours=0.6K, # Tokens=58M2026.0346.247.947.747.3
AL-Whisper-Instruct-RSize=4B, No LLM Modification=✓, # Samples=0.5M, # Hours=1K, # Tokens=91M2026.0345.946.77355.2
MusiLingoSize=7B, No LLM Modification=✓, # Samples=0.7M2026.0343.240.131.238.2
SALMONNSize=13B, No LLM Modification=×, # Samples=2.3M, # Hours=4.4K2026.0341.137.126.434.9
MU-LLaMASize=7B, No LLM Modification=✓, # Samples=0.1M, # Hours=762026.033332.317.427.6
GAMASize=7B, No LLM Modification=×, # Samples=6.3M2026.0331.817.712.920.8
GAMA-ITSize=7B, No LLM Modification=×, # Samples=6.5M2026.0330.926.710.822.8
LTUSize=7B, No LLM Modification=×, # Samples=5.6M2026.0320.41615.917.4