Open Portuguese LLM Leaderboard: leaderboard
Portuguese language LLM evaluation across 9 Brazilian/Portuguese benchmarks including ENEM, BluEx, OAB exams, ASSIN2, FaQuAD, and sentiment analysis.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 42 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 88.37 | #123 |
| 2 | Gemini 2.5 Flash | 85.58 | #245 |
| 3 | Claude 3.7 Sonnet (20250219) | 84.49 | #201 |
| 4 | GPT-5 Mini (2025-08-07) | 83.86 | #172 |
| 5 | GPT-4o (2024-08-06) | 83.82 | #336 |
| 6 | GPT-5 (Minimal) | 83.42 | #98 (GPT-5) |
| 7 | DeepSeek V3.1 | 82.56 | #264 |
| 8 | Gemini 2.0 Flash (001) | 82.3 | #360 |
| 9 | Llama 3.1 405B Instruct | 82.09 | #457 |
| 10 | Kimi K2 | 81.85 | #243 |
| 11 | DeepSeek V3 (0324) | 81.51 | #340 |
| 12 | Qwen 2.5 72B Instruct | 81.06 | #454 |
| 13 | Qwen 2.5 VL 32B Instruct | 80.86 | #453 |
| 14 | Gemini 2.0 Flash Lite (001) | 80.56 | #544 |
| 15 | Llama 4 Maverick Instruct | 80.13 | #456 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-portuguese-llm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.