EuroEval Czech Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 211 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 85.14 |
| 2 | Claude Sonnet 4.5 (Non-reasoning) | 84.15 |
| 3 | Claude Sonnet 4.6 | 81.71 |
| 4 | Gemini 3 Pro (Preview) | 80.82 |
| 5 | Grok 4.20 Beta (0309) (Reasoning) | 79.96 |
| 6 | Gemini 2.5 Pro | 79.68 |
| 7 | Mistral Small 3.1 | 78.4 |
| 8 | GPT-5 | 77.3 |
| 9 | Qwen 2.5 72B Instruct | 76.79 |
| 10 | Gemma 4 31B (IT) | 75.89 |
| 11 | Llama 3.3 70B Instruct | 74.88 |
| 12 | Mistral Small 3.2 | 74.1 |
| 13 | GPT-4.1 | 74.01 |
| 14 | Magistral Small 1.2 | 73.87 |
| 15 | Qwen 3 30B A3B 2507 Instruct | 73.46 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-czech-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.