OpenCodePapers

audio-visual-question-answering-on-lvomnibench

Audio Question AnsweringAudio-visual Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception46.5LEAP (extra data)2026-09-30
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning✓ Link44.7OmniReasoning-30B-A3B (extra data)2026-09-30
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning44.2OmniSeek (ours)2026-10-01
Realtime-Venus: A full-duplex interaction system with asynchronous delegation38.9Realtime-Venus-Omni2026-09-12
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning✓ Link35.1LatentOmni2026-05-21