Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Decomposition on VoxMind Agentic Core Capabilities Dataset
Loading...
95.24
TS
VoxMind
20.9528
40.2389
59.525
78.8111
Apr 17, 2026
TS
PF
Updated 3mo ago
Evaluation Results
Method
Method
Links
TS
PF
VoxMind
2026.04
95.24
38.1
Gemini-2.5-pro
Model Category=Closed-...
2026.04
82.54
52.38
Qwen3-8B+Whisper
Model Category=Open-so...
2026.04
82.54
41.27
Gemini-2.5-flash
Model Category=Closed-...
2026.04
61.9
31.22
StepAudio2
Model Category=Open-so...
2026.04
60.32
26.98
Kimi-Audio
Model Category=Open-so...
2026.04
48.15
22.75
Qwen2.5-Omni
Model Category=Open-so...
2026.04
38.62
3.17
GPT-4o-audio
Model Category=Closed-...
2026.04
23.81
15.87
Feedback
Search any
task
Search any
task