EuroEval Croatian Common Sense Reasoning: leaderboard
EuroEval's Croatian common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Croatian, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 194 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 82.86 | #142 (Claude Sonnet 4.5) |
| 2 | Qwen 3.5 27B FP8 | 81.04 | #164 |
| 3 | Gemini 3 Flash (Preview) (Thinking) | 80.87 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Gemini 3 Pro (Preview) | 78.16 | #66 |
| 5 | GPT-5 | 77.43 | #98 |
| 6 | Qwen 3.5 35B A3B FP8 | 75.61 | #362 |
| 7 | Gemini 2.5 Pro | 73.33 | #152 |
| 8 | Gemini 2.5 Flash (Thinking) | 72.6 | #245 (Gemini 2.5 Flash) |
| 9 | Grok 4.20 Beta (0309) (Reasoning) | 72.03 | #204 (Grok 4.20 Beta (0309)) |
| 10 | Qwen 3.5 9B | 66.6 | #379 |
| 11 | GPT-5 Mini (2025-08-07) | 62.76 | #172 |
| 12 | GPT-4.1 | 62.74 | #248 |
| 13 | Grok 4.1 Fast (Reasoning) | 60.41 | #217 (Grok 4.1 Fast) |
| 14 | Gemma 4 31B (IT) | 59.29 | #176 |
| 15 | Gemini 3 Flash (Preview) (Non-reasoning) | 58.23 | #82 (Gemini 3 Flash (Preview)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-croatian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.