KVoiceBench - KAdvBench: leaderboard

Metric: Refusal rate (%; rule-based detection of refusals to harmful spoken requests transferred from AdvBench; Korean spoken questions synthesized with TTS; single run at temperature 0.7). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1MiniCPM-o-4.548.5

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