EuroEval Slovene: leaderboard

Slovene-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.

Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 208 models tracked.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.5 (Thinking)67.68#142 (Claude Sonnet 4.5)
2GPT-567.41#98
3Gemini 3 Pro (Preview)66.87#66
4Gemini 2.5 Flash (Thinking)66.86#245 (Gemini 2.5 Flash)
5Gemini 2.5 Pro64.81#152
6Gemini 3.1 Flash Lite (Preview)64.01#194
7Gemini 3 Flash (Preview) (Non-reasoning)63.82#82 (Gemini 3 Flash (Preview))
8GPT-5.4 Mini (2026-03-17) (High)63.77#169 (GPT-5.4 Mini (2026-03-17))
9Gemini 3 Flash (Preview) (Thinking)63.52#82 (Gemini 3 Flash (Preview))
10Claude Sonnet 4.662.75#90
11Gemma 4 31B (IT)61.94#176
12Grok 4.1 Fast (Reasoning)61.62#217 (Grok 4.1 Fast)
13GPT-5.261.1#110
14GPT-5 Mini (2025-08-07)60.56#172
15GPT-5.4 Nano (2026-03-17) (High)60.17#266 (GPT-5.4 Nano (2026-03-17))

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 · How It Works · Data refreshed daily, snapshot 2026-10-20.