# VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing

arXiv: https://arxiv.org/abs/2509.22651 · HTML: https://mlsanity.com/paper/2509.22651/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2025.

## Built on by (most cited first, 7 of 7)

- [SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models](https://mlsanity.com/paper/2603.16859/) (2026)
- [SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise](https://mlsanity.com/paper/2602.12783/) (2026)
- [Do What I Say: A Spoken Prompt Dataset for Instruction-Following](https://mlsanity.com/paper/2603.09881/) (2026)
- [OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models](https://mlsanity.com/paper/2603.23938/) (2026)
- [WASIL: In-the-Wild Arabic Spoken Interactions with LLMs](https://mlsanity.com/paper/2605.16364/) (2026)
- [VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context](https://mlsanity.com/paper/2511.08230/) (2025)
- [S3-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants](https://mlsanity.com/paper/2609.09852/) (2026)

## Abstract (arXiv)

The growing capabilities of large language models and multimodal systems have spurred interest in voice-first AI assistants, yet existing benchmarks are inadequate for evaluating the full range of these systems' capabilities. We introduce VoiceAssistant-Eval, a comprehensive benchmark designed to assess AI assistants across listening, speaking, and viewing. VoiceAssistant-Eval comprises 10,497 curated examples spanning 13 task categories. These tasks include natural sounds, music, and spoken dialogue for listening; multi-turn dialogue, role-play imitation, and various scenarios for speaking; and highly heterogeneous images for viewing. To demonstrate its utility, we evaluate 21 open-source models and GPT-4o-Audio, measuring the quality of the response content and speech, as well as their consistency. The results reveal three key findings: (1) proprietary models do not universally outperform open-source models; (2) most models excel at speaking tasks but lag in audio understanding; and (3) well-designed smaller models can rival much larger ones. Notably, the mid-sized Step-Audio-2-mini (7B) achieves more than double the listening accuracy of LLaMA-Omni2-32B-Bilingual. However, challenges remain: multimodal (audio plus visual) input and role-play voice imitation tasks are difficult for current models, and significant gaps persist in robustness and safety alignment. VoiceAssistant-Eval identifies these gaps and establishes a rigorous framework for evaluating and guiding the development of next-generation AI assistants. Code and data will be released at https://mathllm.github.io/VoiceAssistantEval/ .