List your company

Audio Understanding on MMAU v05.15.25 (test)

84.04Sound ScoreStep-Audio 2
18.166435.268252.3769.4718Feb 10, 2026Feb 14, 2026Feb 19, 2026Feb 24, 2026Feb 28, 2026Mar 5, 2026Mar 10, 2026

Evaluation results

MethodLinks
Step-Audio 2Param=32B2026.0284.0473.5675.1577.58
MiMo-AudioParam=7B2026.0281.6874.2568.1774.7
Step-Audio 2Params=32B2026.0280.668.2372.7573.86
Audio Flamingo 3Param=7B2026.0279.5873.9566.3773.3
Step-Audio 2 miniParam=7B2026.0279.368.4468.1672.73
Covo-AudioParam=7B2026.0278.6876.0571.1775.3
Qwen2.5-OmniParam=7B2026.0278.165.970.671.5
MiMo-AudioParams=7B2026.0277.269.7370.7772.59
Qwen2.5-OmniSize=7B, No LLM Modification=×, # Tokens=0.3T2026.0376.867.368.971
Qwen2.5-OmniParams=7B2026.0276.7767.3368.971
Audio Flamingo 3Params=7B2026.0275.8374.4766.9772.42
Audio Flamingo 3Size=8B, No LLM Modification=×, # Samples=26.7M, # Hours=54.4K2026.0375.874.56772.4
Kimi-AudioParam=7B2026.0275.6866.7762.1668.2
Step-Audio 2 miniParams=7B2026.0275.5766.8566.4970.23
Gemini 2.5 ProParam=-2026.0275.0868.2671.4771.6
Covo-AudioParams=7B2026.0273.970.271.5671.89
Gemini 2.5 FlashParam=-2026.0273.2765.5776.5871.8
Audio Flamingo 2Param=3.2B2026.0271.4770.9644.7462.4
Gemini 2.0 FlashParam=-2026.0271.1765.2775.0870.5
Kimi-AudioParams=7B2026.0270.765.9356.5764.4
Gemini 2.5 Pro2026.0270.6364.7772.6769.36
Gemini 2.5 Flash2026.0269.569.468.2767.39
Gemini 2.0 Flash2026.0268.9359.372.8767.03
Audio Flamingo 2Params=3.2B2026.0268.1370.244.8761.06
Audio Flamingo 2Size=3B, No LLM Modification=×, # Samples=5.9M2026.0368.170.244.961.1
Audio ReasonerSize=8B, No LLM Modification=×, # Samples=> 1.2M, # Hours=> 320K2026.0367.361.562.563.8
Qwen2-Audio-InstructParam=8.4B2026.0267.2756.2955.2659.6
DeSTA-2.5-AudioSize=8B, No LLM Modification=✓, # Samples=5M, # Hours=7K2026.0366.957.171.965.2
GPT-4o AudioParam=-2026.0264.5656.2966.6762.5
GPT-4o Audio2026.0263.249.9369.3360.82
GPT-4o Audio2026.0363.249.969.360.8
Phi-4-MultimodalSize=4B, No LLM Modification=×, # Samples=> 28M, # Hours=> 2M2026.0362.76263.862.8
Qwen2-Audio-InstructSize=7B, No LLM Modification=×, # Hours=320K2026.0361.255.755.457.4
Qwen2-Audio-InstructParams=8.4B2026.0261.1755.6755.3757.4
ALARM-CASize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0361.153.361.158.5
AL-SSLAM-RSize=4B, No LLM Modification=✓, # Samples=0.4M, # Hours=1.2K, # Tokens=108M2026.0360.450.947.853
ALARM-ESize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0359.154.273.762.4
ALARM-PSize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0358.553.366.759.5
AL-Whisper-RSize=4B, No LLM Modification=✓, # Samples=5.5M, # Hours=17K, # Tokens=1.5B2026.0355.649.758.854.7
GPT-4o mini AudioParam=-2026.0250.7539.2269.0753
Gemma 3nSize=8B4E2026.0350.253.262.155.2
AL-Whisper-Instruct-RSize=4B, No LLM Modification=✓, # Samples=0.5M, # Hours=1K, # Tokens=91M2026.0349.949.77357.5
GPT-4o mini Audio2026.0349.73667.551
GPT-4o mini Audio2026.0249.6735.9767.4751.03
AL-MuQ-RSize=4B, No LLM Modification=✓, # Samples=0.4M, # Hours=1.5K, # Tokens=137M2026.0349.153.343.148.5
Gemma 3nSize=6B2E2026.0347.551.65752
AL-W2VBERT2-RSize=4B, No LLM Modification=✓, # Samples=0.5M, # Hours=0.6K, # Tokens=58M2026.0346.94648.247
SALMONNSize=13B, No LLM Modification=×, # Samples=2.3M, # Hours=4.4K2026.0342.137.828.836.2
MusiLingoSize=7B, No LLM Modification=✓, # Samples=0.7M2026.0341.941.231.738.3
GAMA-ITSize=7B, No LLM Modification=×, # Samples=6.5M2026.0332.722.411.622.2
MU-LLaMASize=7B, No LLM Modification=✓, # Samples=0.1M, # Hours=762026.033129.717.125.9
GAMASize=7B, No LLM Modification=×, # Samples=6.3M2026.0330.717.316.721.7
LTUSize=7B, No LLM Modification=×, # Samples=5.6M2026.0320.715.715.317.2