AVI-Bench - Reasoning: leaderboard

Metric: Stage score (%) for the reasoning stage: mean of the two hallucination-resistance accuracies, audio-visual question answering and audio-visual language grounding, 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

#ModelScore
1Gemini 2.5 Pro (Preview 05-06)69.06
2Gemini 2.0 Flash64.03
3Gemini 2.5 Flash (Preview 04-17)63.7
4Gemini 1.5 Flash62.82
5Gemini 1.5 Pro61.19
6Qwen2.5-Omni-7B58.26
7Phi-4 Multimodal Instruct50.8

Interactive version: theaggregate.ai/benchmark?slug=avi-bench-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.