EuroEval Portuguese NLU - SST-2 PT — leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 444 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 91.66 |
| 2 | Gemini 3 Pro (Preview) | 90.88 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 89.25 |
| 4 | Ministral-3-14B-Reasoning-2512 | 89.1 |
| 5 | Gemma 4 31B (IT) | 88.97 |
| 6 | Claude Sonnet 4.5 (Thinking) | 88.86 |
| 7 | Gemma 4 26B A4B (IT) | 88.68 |
| 8 | Gemini 3 Flash (Preview) (Non-reasoning) | 88.38 |
| 9 | GPT-5 (High) | 88.2 |
| 10 | Ministral 3 14B | 87.98 |
| 11 | Bielik-11B-v2.3-Instruct | 87.85 |
| 12 | Ministral 3 8B | 87.24 |
| 13 | Ministral-3-14B-Instruct-2512 | 87.08 |
| 14 | gemma-4-E4B-it | 86.93 |
| 15 | GPT-5 | 86.82 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-portuguese-nlu-sst-2-pt · How the rankings work · Data refreshed daily, snapshot 2026-07-22.