EuroEval Serbian Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 188 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 78.7 |
| 2 | Gemini 3 Pro (Preview) | 76.26 |
| 3 | GPT-5 | 74.27 |
| 4 | Gemini 2.5 Pro | 67.99 |
| 5 | Gemini 2.5 Flash (Thinking) | 67.23 |
| 6 | GPT-5 Mini | 64.33 |
| 7 | Claude Sonnet 4.6 | 62 |
| 8 | Claude Sonnet 4.5 (Non-reasoning) | 60.2 |
| 9 | Grok 4.1 Fast (Reasoning) | 59.6 |
| 10 | Qwen 3.5 9B | 59.53 |
| 11 | GPT-4.1 | 57.8 |
| 12 | Gemma 4 31B (IT) | 56.22 |
| 13 | GPT-5.4 Mini (High) | 55.29 |
| 14 | Qwen 3.5 4B | 53.85 |
| 15 | Qwen 2.5 72B Instruct | 51.51 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-serbian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.