EuroEval Portuguese NLU - ScaLA PT: leaderboard
The "ScaLA PT" subtask of EuroEval Portuguese NLU. Portuguese-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Around 2029. 444 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 76.33 | #91 |
| 2 | Gemini 3 Pro (Preview) | 74.07 | #65 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 71.96 | #196 |
| 4 | GPT-5.2 | 71.49 | #110 |
| 5 | Gemini 3 Flash (Preview) (Non-reasoning) | 71.42 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Gemma 4 31B (IT) | 71.04 | #176 |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 68.66 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemma 4 26B A4B (IT) | 66.44 | #295 |
| 9 | GPT-5.4 Mini (2026-03-17) (High) | 65.02 | #170 (GPT-5.4 Mini (2026-03-17)) |
| 10 | GPT-5.4 Nano (2026-03-17) (High) | 64.73 | #266 (GPT-5.4 Nano (2026-03-17)) |
| 11 | Grok 4.1 Fast (Reasoning) | 63.82 | #217 (Grok 4.1 Fast) |
| 12 | Qwen 3.5 35B A3B Base | 58.62 | #309 |
| 13 | Llama 3.1 70B | 57.59 | #592 |
| 14 | Qwen 3.5 9B | 56.24 | #384 |
| 15 | gemma-3-27B-pt | 55.59 | #503 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-portuguese-nlu-scala-pt · How It Works · Data refreshed daily, snapshot 2026-10-21.