OpenCodePapers

audio-visual-question-answering-on-omnivideobench

Audio Question AnsweringAudio-visual Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding✓ Link59.1OmniAgent2025-12-29
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning✓ Link50.0OmniReasoning-30B-A3B (extra data)2026-09-30
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning47.7OmniSeek (ours)2026-10-01
Omni-Streaming Thinking✓ Link46.6OST2026-09-14
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering✓ Link40.50OmniJigsaw (CMM)2026-04-09
Realtime-Venus: A full-duplex interaction system with asynchronous delegation39.2Realtime-Venus-Omni2026-09-12
CogniRoute: Learning to Route Social Evidence in Omni-Modal Models38.9CogniRoute2026-06-18
Native Active Perception as Reasoning for Omni-Modal Understanding✓ Link37.1OmniAgent-RL-7B2026-06-17
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs✓ Link36.9Ola (7B) +OFF2026-01-20
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning✓ Link35.4LatentOmni2026-05-21
Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data✓ Link35.1Uni-MoE-2.0-Omni2025-11-16
Check out how to contribute new results. Then edit this file on GitLab or GitHub.