EuroEval Slovene NLU - Sentinews: leaderboard
The "Sentinews" subtask of EuroEval Slovene NLU. Slovene-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 January 2027. 204 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B (IT) | 58.61 | #176 |
| 2 | Gemini 3 Flash (Preview) (Thinking) | 58.33 | #82 (Gemini 3 Flash (Preview)) |
| 3 | Ministral-3-8B-Instruct-2512 | 56.34 | #661 |
| 4 | Gemini 3 Flash (Preview) (Non-reasoning) | 56.26 | #82 (Gemini 3 Flash (Preview)) |
| 5 | Gemini 2.5 Flash (Thinking) | 56.2 | #245 (Gemini 2.5 Flash) |
| 6 | Grok 4.1 Fast (Reasoning) | 55.07 | #217 (Grok 4.1 Fast) |
| 7 | Claude Sonnet 4.6 | 55.02 | #90 |
| 8 | Gemini 2.5 Pro | 54.42 | #152 |
| 9 | Ministral-3-14B-Reasoning-2512 | 54.37 | #540 |
| 10 | Gemini 3.1 Flash Lite (Preview) | 54.25 | #194 |
| 11 | Bielik-11B-v2.3-Instruct | 54.25 | #693 |
| 12 | Ministral-3-14B-Instruct-2512 | 54.21 | #615 |
| 13 | Gemma 4 26B A4B (IT) | 54.04 | #297 |
| 14 | GPT-4.1 | 54 | #248 |
| 15 | GPT-4.1 Mini | 53.77 | #355 |
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-sentinews · How It Works · Data refreshed daily, snapshot 2026-10-20.