List your company

Audiovisual Understanding & Reasoning on Daily-Omni

80.2ScoreMiniCPM-o 4.5
15.574432.352249.1365.9078Feb 17, 2026Mar 9, 2026Mar 29, 2026Apr 18, 2026May 8, 2026May 28, 2026Jun 17, 2026

Evaluation results

MethodLinks
MiniCPM-o 4.5Size=9B2026.0680.2
TAC-VArchitecture=Describer + Text-only Reasoner, Reasoner=Gemini32026.0277.9
Ours(Qwen3-Omni)Size=30B2026.0676.61
Qwen3-OmniArchitecture=Native MLLM2026.0276.2
Gemini2.5-Pro-MTSSModel Category=Proprietary, Scripting Paradigm=MTSS2026.0475.68
Qwen3-OmniSize=30B2026.0674.27
TAC-VArchitecture=Describer + Text-only Reasoner, Reasoner=Qwen32026.0272.9
Gemini 2.5 FlashArchitecture=Native MLLM2026.0272.7
Ours(Qwen2.5-Omni)Size=7B2026.0669.84
Gemini2.5-ProModel Category=Proprietary, Scripting Paradigm=Monolithic2026.0468.25
OmniVinciArchitecture=Native MLLM2026.0266.5
OmniAgentSize=7B2026.0664.8
Uni-MoE-2.0-OmniSize=30B2026.0664.33
video-SALMONN 2+Size=7B2026.0662.57
Qwen2.5-OmniSize=7B2026.0662.41
Qwen3.5-Omni-Flash-MTSSModel Category=Proprietary, Scripting Paradigm=MTSS2026.0461.45
OmniVinciSize=9B2026.0661.32
Qwen2.5-OmniSize=7B2026.0660.1
Qwen3-Omni-MTSS-FTModel Category=Open-Source, Scripting Paradigm=MTSS, Evaluation Protocol=Fine-tuned2026.0459.45
ASID-Captioner-7BModel Category=Open-Source2026.0458.56
GPT-4o2026.0656.5
Gemini-2.0-Flash2026.0656.1
AVoCaDOModel Category=Open-Source2026.0455.72
Ours(VITA-1.5)Size=8B2026.0655.39
MiniCPM-oSize=8B2026.0653.1
VITA-1.5Size=8B2026.0652.63
VLMArchitecture=Describer + Text-only Reasoner, Reasoner=Qwen32026.0251.5
OlaSize=7B2026.0650.7
Qwen3-Omni-MTSSModel Category=Open-Source, Scripting Paradigm=MTSS2026.0441.17
Qwen3.5-Omni-FlashModel Category=Proprietary, Scripting Paradigm=Monolithic2026.0437.71
VideoLLaMA2Size=7B2026.0635.2
Unified-IO-2Size=8B2026.0628.2
Qwen3-OmniModel Category=Open-Source, Scripting Paradigm=Monolithic2026.0418.06