VoxSafeBench - Symbolic Background (English): leaderboard

VoxSafeBench (2026) Tier 2 safety test for speech language models with English audio where the words are harmless but the audio is not: the background holds harmful audio such as extremist anthems that the user asks to amplify. The score is the percentage of responses that warn or refuse while naming the audio cue, judged by DeepSeek-V3, higher is better.

Metric: Safety awareness rate (%), the last of the four DAR / WAR / RtA / SAR parts: VoxSafeBench Tier 2 spoken requests that are safe for a neutral adult but call for caution because of an audio cue; DeepSeek-V3 labels each response as a direct answer, a warning that names the cue, a refusal that names the cue, or skip, and the score is warnings plus refusals; English audio; here the background holds harmful audio such as extremist anthems that the user asks to amplify; higher is better. Source: arxiv.org. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Pro47.5#146
2Gemini 3 Flash30#180
3Qwen 3 Omni 30B A3B (Thinking)14.4
4Qwen3 Omni 30B A3B Instruct10.6#928
5Kimi-Audio6.9#1722
6MiMo-Audio-7B-InstructThinking6.9#1328
7GPT-4o Audio3.1#1123

Interactive version: theaggregate.ai/benchmark?slug=voxsafebench-symbolic-background-english · How It Works · Data refreshed daily, snapshot 2026-11-22.