EuroEval Slovene NLU: leaderboard
Slovene-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: NLU Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 208 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 63.65 | #245 (Gemini 2.5 Flash) |
| 2 | Gemini 3 Pro (Preview) | 63.1 | #66 |
| 3 | GPT-5.4 Mini (2026-03-17) (High) | 62.43 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 4 | GPT-5 | 61.79 | #98 |
| 5 | Gemini 3.1 Flash Lite (Preview) | 61.49 | #194 |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 61.31 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Claude Sonnet 4.5 (Thinking) | 61.29 | #142 (Claude Sonnet 4.5) |
| 8 | Gemma 4 31B (IT) | 60.75 | #176 |
| 9 | Claude Sonnet 4.6 | 60.66 | #90 |
| 10 | Gemini 3 Flash (Preview) (Thinking) | 60.53 | #82 (Gemini 3 Flash (Preview)) |
| 11 | Gemini 2.5 Pro | 59.59 | #152 |
| 12 | GPT-5.2 | 59.15 | #110 |
| 13 | gemma-3-27B-pt | 58.34 | #502 |
| 14 | Gemini 2.5 Flash Lite (Thinking) | 58.16 | #422 (Gemini 2.5 Flash Lite) |
| 15 | Llama 3.1 70B | 57.94 | #592 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovene-nlu · How It Works · Data refreshed daily, snapshot 2026-10-20.