Open Portuguese LLM - TweetSentBR — leaderboard
Metric: F1 (%). Source: huggingface.co. 42 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (2025-08-07) | 78.78 |
| 2 | Claude 3.7 Sonnet (20250219) | 78.42 |
| 3 | Llama 3.1 405B Instruct | 78.21 |
| 4 | Gemini 2.5 Flash | 78.01 |
| 5 | GPT-4o (2024-08-06) | 77.61 |
| 6 | Gemini 2.5 Flash Lite | 76.96 |
| 7 | Gemini 2.0 Flash Lite (001) | 76.76 |
| 8 | Gemini 2.0 Flash (001) | 76.53 |
| 9 | Qwen 2.5 72B Instruct | 76.2 |
| 10 | DeepSeek V3.1 | 75.84 |
| 11 | GPT-4o Mini (2024-07-18) | 75.09 |
| 12 | Gemma 3 27B (IT) | 74.49 |
| 13 | Kimi K2 | 74.28 |
| 14 | GPT-5 Nano | 73.86 |
| 15 | Gemini 1.5 Flash-8B (001) | 73.77 |
Interactive version: theaggregate.ai/benchmark?slug=open-portuguese-llm-tweetsentbr · How the rankings work · Data refreshed daily, snapshot 2026-07-22.