AGIBOT's WITA-Omni Preview Achieves Top Score in Audio-Visual Reasoning Benchmark
- Published
AGIBOT announced that its WITA-Omni Preview multimodal foundation model has achieved the highest score on the Daily-Omni audio-visual reasoning benchmark, surpassing models from Alibaba, Google, and ByteDance. The model recorded an average accuracy of 85.21 percent, excelling in audio-visual alignment, event sequencing, and various evaluation metrics.
This achievement is significant as it demonstrates WITA-Omni Preview's advanced capabilities in understanding and reasoning across audio and visual information, which are crucial for embodied AI systems in dynamic environments. The benchmark evaluates models on their ability to associate sounds with visible events and understand the progression of situations, highlighting the importance of these skills in real-world applications.
Looking ahead, AGIBOT's WITA-Omni model is designed to enhance human-robot interactions by integrating movement and facial expressions with speech. The company has developed a human-centric multimodal interaction dataset to further improve the model's performance. No further timeline was disclosed at the time of publication.
Original report
AGIBOT’s foundation model tops benchmark test for audio-visual reasoning
RoboticsAndAutomationNews.com · David EdwardsThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
-
1
RobotToday Weekly November 2 – 6, 2026 RobotToday · 6 hours ago
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
-
10
RobotToday Weekly October 26 – 30, 2026 RobotToday · 1 week ago
- 11
- 12
Related Suppliers
Agibot 智元机器人
China
Shanghai humanoid-robot manufacturer founded 2023; builds A-series, X-series and D1 quadruped robots and has produced more than 15,000 units to date.
Google DeepMind
United Kingdom
Alphabet's London-based AI lab, developer of the Gemini Robotics vision-language-action models and the open-source MuJoCo physics simulator.
Google Ventures (GV)
United States
Alphabet's independent venture capital arm investing in life sciences, AI, robotics, and enterprise technology
Scentience
United States
US startup designing neuromorphic olfactory sensors, edge AI models, and developer APIs to give robots a sense of smell for navigation, security, and.
Beijing Ribri Technology Co., Ltd.
China
Chinese developer of opto-acoustic systems, long-range acoustic hailers, acoustic C-UAS detection and sonar payloads for unmanned and security platforms.
Tekpoint GmbH
Austria
Vienna B2B tech distributor founded 2009 with 120+ staff; AGIBOT's European humanoid distributor and a reseller of Roborock and Navimow home robots.
Human Archive
United States
Data lab capturing aligned multimodal human-interaction data to train robotics and embodied-AI foundation models.
Yaak Technologies GmbH
Germany
Berlin AI startup founded 2020, collecting multimodal driving data across 30+ German cities to train foundation models for autonomous vehicles and robotics.
Tommoro Robotics 투모로 로보틱스
Korea, Republic of (South)
Tommoro Robotics (Korea, f. 2022, SNU spinout) builds Robot Foundation Models and Physical AI software for humanoids and collaborative robots targeting.
Tera AI
United States
San Francisco AI startup providing software-only spatial reasoning and visual navigation for robots, enabling GPS-free positioning using onboard cameras.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
