EuroEval Serbian Common Sense Reasoning: leaderboard
EuroEval's Serbian common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Serbian, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 188 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 78.7 | #142 (Claude Sonnet 4.5) |
| 2 | Gemini 3 Pro (Preview) | 76.26 | #66 |
| 3 | GPT-5 | 74.27 | #98 |
| 4 | Gemini 2.5 Pro | 67.99 | #152 |
| 5 | Gemini 2.5 Flash (Thinking) | 67.23 | #245 (Gemini 2.5 Flash) |
| 6 | GPT-5 Mini (2025-08-07) | 64.33 | #172 |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 63.95 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Claude Sonnet 4.6 | 62 | #90 |
| 9 | Claude Sonnet 4.5 (Non-reasoning) | 60.2 | #142 (Claude Sonnet 4.5) |
| 10 | Grok 4.1 Fast (Reasoning) | 59.6 | #217 (Grok 4.1 Fast) |
| 11 | Qwen 3.5 9B | 59.53 | #379 |
| 12 | GPT-4.1 | 57.8 | #248 |
| 13 | Gemini 3 Flash (Preview) (Non-reasoning) | 57.1 | #82 (Gemini 3 Flash (Preview)) |
| 14 | Gemma 4 31B (IT) | 56.22 | #176 |
| 15 | GPT-5.4 Mini (2026-03-17) (High) | 55.29 | #169 (GPT-5.4 Mini (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-serbian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.