EuroEval Slovak Common Sense Reasoning: leaderboard

EuroEval's Slovak common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Slovak, from the EuroEval European language model benchmark suite.

Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 189 models tracked.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.5 (Thinking)77.5#142 (Claude Sonnet 4.5)
2Gemini 2.5 Flash (Thinking)74.26#245 (Gemini 2.5 Flash)
3Gemini 3 Pro (Preview)73.56#66
4Qwen 3 235B A22B 2507 FP8 (Thinking)72.99#246 (Qwen 3 235B A22B 2507 FP8)
5GPT-572.04#98
6Gemini 2.5 Pro71.26#152
7Gemini 3 Flash (Preview) (Thinking)63.47#82 (Gemini 3 Flash (Preview))
8Gemini 3.1 Flash Lite (Preview)61.43#194
9GPT-5 Mini (2025-08-07)61.18#172
10GPT-4.160.28#248
11Gemini 3 Flash (Preview) (Non-reasoning)59.93#82 (Gemini 3 Flash (Preview))
12Claude Sonnet 4.659.69#90
13GPT-5.4 Mini (2026-03-17) (High)57.99#169 (GPT-5.4 Mini (2026-03-17))
14Qwen 3.5 9B57.55#379
15Grok 4.1 Fast (Reasoning)57.51#217 (Grok 4.1 Fast)

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovak-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.