EuroEval Czech: leaderboard
Czech-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Around March 2027. 236 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 70.02 | #152 |
| 2 | GPT-5 | 68.77 | #98 |
| 3 | Gemini 2.5 Flash (Thinking) | 67.83 | #245 (Gemini 2.5 Flash) |
| 4 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 66.76 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 66.63 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Claude Sonnet 4.5 (Thinking) | 64.39 | #142 (Claude Sonnet 4.5) |
| 7 | Gemini 3 Pro (Preview) | 64.35 | #66 |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 63.96 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Qwen 3.5 27B FP8 | 63.66 | #164 |
| 10 | Claude Sonnet 4.6 | 63.01 | #90 |
| 11 | Gemini 3 Flash (Preview) (Non-reasoning) | 62.65 | #82 (Gemini 3 Flash (Preview)) |
| 12 | Gemini 3.1 Flash Lite (Preview) | 62.11 | #194 |
| 13 | Magistral Small 1.2 | 61.76 | #570 |
| 14 | Qwen 3.5 35B A3B FP8 | 59.58 | #362 |
| 15 | Qwen 3.5 35B A3B Base | 59.54 | #310 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-czech · How It Works · Data refreshed daily, snapshot 2026-10-20.