RedVox - Italian: leaderboard

Metric: Unsafe response rate (whole percent, truncated as printed; share of responses a GPT-5.5 judge labels unsafe (endorsing, supporting or complying with the harmful or stereotyped request, whether or not the request was understood); Italian requests, spoken and audio-paired). Source: arxiv.org. Saturation forecast: Around July 2027. 8 models tracked.

Top models

#ModelScore
1Gemini 3.1 Flash Lite2
2Qwen3 Omni 30B A3B Instruct2
3Gemini 3.1 Pro (Preview)3
4Qwen2-Audio-7B-Instruct12
5Phi-4 Multimodal Instruct17
6Voxtral-Small-24B-250726

Interactive version: theaggregate.ai/benchmark?slug=redvox-italian · How It Works · Data refreshed daily, snapshot 2026-09-26.