AVI-Bench - Audio-Visual Matching: leaderboard
Metric: Task score (%) on audio-visual matching (250 videos): accuracy of the yes, no or not sure verdict on whether the audio and the visual stream belong together, on AVI-Bench (5,864 audio-visual items in 14 tasks over four cognitive stages), zero-shot with the same prompts for every omni-modal model; task scores normalized to percentages; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen2.5-Omni-7B | 78.4 |
| 2 | Gemini 2.5 Pro (Preview 05-06) | 76.8 |
| 3 | Gemini 2.0 Flash | 65.6 |
| 4 | Gemini 2.5 Flash (Preview 04-17) | 61.2 |
| 5 | Gemini 1.5 Pro | 56.8 |
| 6 | Gemini 1.5 Flash | 54.4 |
| 7 | Phi-4 Multimodal Instruct | 52.4 |
Interactive version: theaggregate.ai/benchmark?slug=avi-bench-audio-visual-matching · How It Works · Data refreshed daily, snapshot 2026-09-29.