Open Portuguese LLM - HateBR Offensive — leaderboard

Metric: F1 (%). Source: huggingface.co. 42 models tracked.

Top models

#ModelScore
1GPT-4o (2024-08-06)93.2
2GPT-5 Mini (2025-08-07)93.06
3GPT-5 (2025-08-07)92.33
4DeepSeek V3.192.12
5GPT-5 Nano91.7
6Claude 3.7 Sonnet (20250219)91.25
7Gemini 1.5 Flash (001)90.92
8Llama 3.1 405B Instruct90.74
9DeepSeek V3 (0324)90.6
10Llama 4 Maverick Instruct90.48
11Gemini 1.5 Flash (002)90.46
12Llama 3.3 70B Instruct90.24
13Llama 3.2 90B Vision Instruct89.65
14Kimi K289.42
15Gemini 2.5 Flash89.33

Interactive version: theaggregate.ai/benchmark?slug=open-portuguese-llm-hatebr-offensive · How the rankings work · Data refreshed daily, snapshot 2026-07-22.