VoiceBench Avg
VoiceBench is the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants, evaluating capabilities including general knowledge, instruction-following, reasoning, and safety using both synthetic and real spoken instruction data with diverse speaker characteristics and environmental conditions.
Qwen2.5-Omni-7B from Alibaba Cloud / Qwen Team currently leads the VoiceBench Avg leaderboard with a score of 0.741 across 1 evaluated AI models.
What VoiceBench Avg measures
VoiceBench Avg is a multimodal benchmark that evaluates large language models on reasoning, safety, speech to text, general, and communication tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.7, with the leader reaching 0.7.
Compare leaders on the best AI for reasoning, best AI for safety, best AI for speech to text, best AI for general and best AI for communication leaderboards.
Publication
- Paper
- VoiceBench: Benchmarking LLM-Based Voice Assistants
- Authors
- Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, and 2 others
- Published
- arXiv
- 2410.17196
Abstract
Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world scenarios that involve diverse speaker characteristics, environmental and content factors. To address this, we introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations. Extensive experiments reveal the limitations of current LLM-based voice assistant models and offer valuable insights for future research and development in this field.
Qwen2.5-Omni-7B leads with 74.1%.
Progress Over Time
Interactive timeline showing model performance evolution on VoiceBench Avg
VoiceBench Avg Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 7B | — | — |
FAQ
Common questions about VoiceBench Avg.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions