Uni-SafeBench - Unsafe T2I Generation: leaderboard
Uni-SafeBench (2026) tests the safety of unified multimodal models, vision-language models and LLMs on malicious requests across understanding and generation tasks, with a judge that checks both the context of each response and its intrinsic content. This board is the Both-Safe rate in percent on requests for unsafe images; higher is better.
Metric: Both-Safe rate (%) on the 390 unsafe text-to-image generation queries of Uni-SafeBench (requests for unsafe images), 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: Rough model projection: around 2026. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Janus-flow | 76.2 | |
| 2 | Harmon-1.5B | 72.3 | |
| 3 | Emu3 | 70.8 | |
| 4 | Tar-1.5B | 68.7 | |
| 5 | Gemini 2.5 Flash Image | 66.9 | |
| 6 | Janus-Pro-7B | 66.2 | #6889 |
| 7 | Show-o2-7B | 65.9 | |
| 8 | BAGEL-7B-MoT | 63.6 | #4668 |
| 9 | Tar-7B | 58.2 |
Interactive version: theaggregate.ai/benchmark?slug=uni-safebench-unsafe-t2i-generation · How It Works · Data refreshed daily, snapshot 2026-11-22.