SuperCLUE-DSPSafeBench - Overall: leaderboard
SuperCLUE-DSPSafeBench is a Chinese LLM content-safety benchmark across content risk categories. Headline board of the newest workbook the superclueai.com vertical lists; score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Yi-1.5-9B-Chat-16K | 79.37 | #1120 |
| 2 | Phi-3 Mini 4K Instruct | 78.62 | #1257 |
| 3 | InternLM2.5-Chat-7B | 77.64 | #1009 |
| 4 | Qwen 2.5 7B Instruct | 73.51 | #863 |
| 5 | Mistral 7B Instruct (v0.3) | 73.04 | #1255 |
| 6 | GLM-4 9B Chat | 72.43 | #911 |
| 7 | Gemma 2 9B (IT) | 72.34 | #795 |
| 8 | Qwen 2.5 1.5B Instruct | 71.26 | #1393 |
| 9 | Gemma 2 2B (IT) | 70.42 | #1328 |
| 10 | Baichuan2-7B-Chat | 65.31 | #1384 |
| 11 | Llama 3.1 8B Instruct | 61.51 | #1017 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-dspsafebench-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.