Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio-Language Model Evaluation on ALME
Loading...
72
nAUC (0-5 pp budget)
GACL
-0.8
18.1
37
55.9
Jun 3, 2026
nAUC (0-5 pp budget)
nAUC (0-10 pp budget)
Updated 1mo ago
Evaluation Results
Method
Method
Links
nAUC (0-5 pp budget)
nAUC (0-10 pp budget)
GACL
Model=Voxtral-Small
2026.06
72
76
GACL
Model=Qwen2.5-Omni
2026.06
66
66
GACL
Model=Qwen3-Omni
2026.06
64
64
GACL
Model=Qwen2-Audio-Inst.
2026.06
60.4
63.4
AAD
Model=Qwen2.5-Omni
2026.06
54.8
56.4
GACL
Model=Kimi-Audio-Inst.
2026.06
47
47
AAD
Model=Qwen3-Omni
2026.06
44.7
45
AAD
Model=Qwen2-Audio-Inst.
2026.06
39.5
43.7
ACD
Model=Qwen2.5-Omni
2026.06
32.8
41.2
ACD
Model=Qwen2-Audio-Inst.
2026.06
21.5
26.8
AAD
Model=Voxtral-Small
2026.06
17.9
29.4
ACD
Model=Qwen3-Omni
2026.06
5.2
5.2
ACD
Model=Kimi-Audio-Inst.
2026.06
2.2
4.1
ACD
Model=Voxtral-Small
2026.06
2.1
7
AAD
Model=Kimi-Audio-Inst.
2026.06
2
4.2
Feedback
Search any
task
Search any
task