UbuntuGuard - Cross-Lingual: leaderboard

Metric: F1 (%) for PASS/FAIL policy-compliance classification of user-agent dialogues, English policies with dialogues in ten African languages. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.

Top models

#ModelScore
1Llama 3.3 70B Instruct87.62
2gpt-oss-safeguard-20B84.85
3DeepSeek V3.183.14
4GPT-OSS-20B81.36
5GPT-OSS-120B80.25

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