EuroEval Slovene Common Sense Reasoning — leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 187 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 82.69 |
| 2 | GPT-5 | 74.61 |
| 3 | Gemini 2.5 Flash (Thinking) | 72.09 |
| 4 | Gemini 2.5 Pro | 69.8 |
| 5 | Gemini 3 Pro (Preview) | 68.89 |
| 6 | GPT-5 Mini | 65.54 |
| 7 | Gemini 3.1 Flash Lite (Preview) | 63.34 |
| 8 | Grok 4.1 Fast (Reasoning) | 63.13 |
| 9 | Qwen 3.5 9B | 61.81 |
| 10 | GPT-4.1 | 59.48 |
| 11 | Gemma 4 31B (IT) | 58.68 |
| 12 | Qwen 3.5 4B | 57.96 |
| 13 | Claude Sonnet 4.6 | 57.87 |
| 14 | Gemini 3 Flash (Preview) (Non-reasoning) | 57.75 |
| 15 | GPT-5.4 Nano (High) | 53.8 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovene-common-sense-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.