EuroEval Albanian NLU - ScaLA SQ: leaderboard
The "ScaLA SQ" subtask of EuroEval Albanian NLU. Albanian-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 April 2027. 201 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78.55 | #58 |
| 2 | Gemini 3 Pro (Preview) | 72.43 | #66 |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 64.8 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Gemini 3.1 Flash Lite (Preview) | 62.3 | #194 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 59.48 | #82 (Gemini 3 Flash (Preview)) |
| 6 | GPT-4.1 | 56.9 | #248 |
| 7 | Gemma 4 31B (IT) | 52.54 | #176 |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 50.57 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Gemini 2.5 Pro | 50.19 | #152 |
| 10 | GPT-5 | 49.03 | #98 |
| 11 | Gemma 3 27B (IT) | 48.65 | #523 |
| 12 | Qwen 3.5 27B FP8 | 47.86 | #164 |
| 13 | Gemini 2.5 Flash (Thinking) | 47.44 | #245 (Gemini 2.5 Flash) |
| 14 | Grok 4.20 Beta (0309) (Reasoning) | 46.97 | #204 (Grok 4.20 Beta (0309)) |
| 15 | Gemini 2.5 Flash (Non-reasoning) | 46.57 | #245 (Gemini 2.5 Flash) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-albanian-nlu-scala-sq · How It Works · Data refreshed daily, snapshot 2026-10-20.