EuroEval Albanian NLU - MMS SQ: leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 201 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Small 3.1 | 30.53 |
| 2 | Claude Sonnet 4.6 | 30.21 |
| 3 | Mistral Small 3.2 | 29.62 |
| 4 | Gemini 3.1 Pro (Preview) | 29.46 |
| 5 | Gemma 3 27B (IT) | 29.39 |
| 6 | GPT-5.4 Mini (High) | 29.39 |
| 7 | GPT-5.4 Nano (High) | 29.38 |
| 8 | Gemini 2.5 Pro | 28.98 |
| 9 | GPT-5.2 | 28.93 |
| 10 | Qwen 3 30B A3B 2507 Instruct | 28.48 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 28.43 |
| 12 | GPT-OSS-20B (Medium) | 27.91 |
| 13 | Gemini 3 Pro (Preview) | 27.59 |
| 14 | GPT-5 Mini | 27.51 |
| 15 | Gemma 3n E4B (IT) | 27.43 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-albanian-nlu-mms-sq · How It Works · Data refreshed daily, snapshot 2026-09-05.