EuroEval Portuguese Common Sense Reasoning: leaderboard
EuroEval's Portuguese common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Portuguese, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around April 2027. 395 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 98.75 | #66 |
| 2 | Claude Sonnet 4.5 (Non-reasoning) | 98.65 | #142 (Claude Sonnet 4.5) |
| 3 | Claude Sonnet 4.5 (Thinking) | 98.45 | #142 (Claude Sonnet 4.5) |
| 4 | Gemma 4 31B (IT) | 97.87 | #176 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 97.71 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Claude Sonnet 4.6 | 96.68 | #90 |
| 7 | Gemini 2.5 Pro (Preview 03-25) | 96.07 | #123 |
| 8 | Gemini 3 Flash (Preview) (Non-reasoning) | 95.25 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Qwen 3 235B A22B 2507 Instruct | 94.91 | #300 |
| 10 | GPT-4o (2024-05-13) | 94.53 | #325 |
| 11 | Gemini 2.5 Pro | 93.37 | #152 |
| 12 | Mistral Small 3.1 | 93.34 | #610 |
| 13 | Gemini 2.5 Flash (Non-reasoning) | 93.06 | #245 (Gemini 2.5 Flash) |
| 14 | Grok 3 | 93.05 | #304 |
| 15 | Mistral Small 3 | 92.94 | #627 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-portuguese-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.