Audio Understanding on MMAU (test)

76.58Speech Score

Gemini 2.5 Flash

Updated 1mo ago

Evaluation Results

Method
Gemini 2.5 Flash 2025.12	76.58	73.27	65.57	71.8	-
Gemini 2.0 Flash 2026.01	72.87	68.93	59.3	67.03	-
Qwen2.5-Omni 2025.12	70.6	78.1	65.9	71.5	-
DIFFA-2 2026.01	70.18	70.83	60.1	67	-
DIFFA-2 2026.01	70.15	69.43	59.57	66.34	-
GPT-4o-Audio 2026.01	69.33	63.2	49.93	60.82	-
MiMo-Audio-7B-Instruct 2025.12	68.47	82.58	73.65	74.9	-
Step-Audio2-mini 2025.12	68.16	79.3	68.44	72.73	-
Qwen2.5-Omni 2026.01	67.93	69.53	62.5	66.64	-
Qwen3-Omni 2026.01	66.46	73.7	72.22	70.77	-
Audio Flamingo 3 2025.12	66.37	79.58	66.77	73.3	-
Phi-4-multimodal 2026.01	63.8	62.67	61.97	62.81	-
Kimi-Audio-Instruct 2025.12	62.16	75.68	66.77	68.2	-
Qwen2-Audio-7B-Instruct (Base Model) 2026.01	58.73	64.74	58.98	60.81	-
Kimi-Audio 2026.01	56.57	70.7	65.93	64.4	-
CORD 2026.01	55.42	64.44	60.18	60.01	-
Qwen2-Audio 2026.01	55.37	61.17	55.67	57.4	-
Qwen2-Audio-7B-Instruct + Forward KL 2026.01	53.01	61.7	55.99	56.9	-
Qwen2-Audio-7B-Instruct + SFT 2026.01	51.51	64.44	56.29	57.39	-
Baichuan-Audio 2026.01	42.47	59.46	49.1	50.34	-
GLM-4-Voice 2025.12	35.44	27.63	27.84	30.3	-
GLM-4-Voice 2026.01	35.44	27.63	27.84	30.3	-
Salmonn 2026.01	28.77	42.1	37.83	36.23	-
Qwen-Audio-Chat 2026.01	27.95	56.73	40.9	41.86	-
LTU 2026.01	15.33	20.67	15.68	17.23	-
Kimi-Audio 2025.12	-	-	-	-	69.6
Audio-Flamingo 2025.12	-	-	-	-	73.3
Step-Audio2-Mini 2025.12	-	-	-	-	73.2
MiMo-Audio 2025.12	-	-	-	-	74.9
Fun-Audio-Chat 2025.12	-	-	-	-	77.9
Fun-Audio-Chat 2025.12	-	-	-	-	76.6