Loading
Loading
This benchmark tests how LLM manage semantic and emotional exception in Brazilian Portuguese expressions
The questions are made by Matteo Sisti
62
Total Prompts
905
Scored Responses
4
Contributors
31%
Average Overall Score
| Rank | Model | Avg. Score | Prompts Tested | Avg. Response Time |
|---|---|---|---|---|
| Rank | Model | Avg. Score | Prompts Tested | Avg. Response Time |
|---|---|---|---|---|
1 | openai/gpt-5.2 | 0.46 | 62 | 7ms |
2 | google/gemini-3-pro-preview | 0.39 | 62 | 38ms |
3 | x-ai/grok-4 | 0.38 | 62 | 54ms |
4 | qwen/qwen3-235b-a22b-2507 | 0.35 | 62 | 4ms |
5 | x-ai/grok-4.1-fast | 0.34 | 62 | 16ms |