Uni-SafeBench - Malicious Text Generation: leaderboard
Metric: Both-Safe rate (%) on the 630 malicious text generation queries of Uni-SafeBench (text-only requests for harmful text), judged by the Uni-Judger framework (malicious-intent extractor plus safety detector on Qwen3-VL-8B-Instruct), a response counts as safe only when it is safe or a refusal in the context of the extracted intent and its own content is not intrinsically unsafe, mean over repeated judge runs; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 98.7 |
| 2 | GPT-4o | 98.1 |
| 3 | Qwen 2.5 7B Instruct | 98.1 |
| 4 | deepseek-llm-7B-chat | 91.7 |
Interactive version: theaggregate.ai/benchmark?slug=uni-safebench-malicious-text-generation · How It Works · Data refreshed daily, snapshot 2026-10-07.