CIBuzzBench - Harmfulness Detection (Chinese Prompt): leaderboard

Metric: Macro F1 (%; binary harmful or non-harmful classification of the documented online sense from the buzzword alone, 14.2% of entries harmful; Chinese instructions; 3,001 Chinese internet buzzwords; zero-shot, temperature 0; the Chinese buzzword is the input under both prompt languages). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)79.86
2GLM-5.278.39
3GPT-5.577.41
4Qwen 3.7 Max76.1
5DeepSeek V4 Pro74.68
6Claude Opus 4.870.41
7Qwen 3 14B63.31
8Qwen 3 8B62.55
9Qwen 3 4B22.83

Interactive version: theaggregate.ai/benchmark?slug=cibuzzbench-harmfulness-detection-chinese-prompt · How It Works · Data refreshed daily, snapshot 2026-09-26.