HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
Open paper
Benchmark
Model
Rank
Results
audio-visual-question-answering-on-worldsense
HumanOmniV2-7B
#13
Accuracy: 47.1
audio-visual-question-answering-on-dailyomni
HumanOmniV2-7B
#18
Accuracy: 58.47
Rank counts only results with a code link.