EuroEval Dutch Common Sense Reasoning: leaderboard
EuroEval's Dutch common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Dutch, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around June 2027. 319 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 93.05 | #142 (Claude Sonnet 4.5) |
| 2 | Claude Sonnet 4.5 (Thinking) | 93.04 | #142 (Claude Sonnet 4.5) |
| 3 | Gemini 3 Flash (Preview) (Thinking) | 86.12 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Gemini 3 Flash (Preview) (Non-reasoning) | 85.36 | #82 (Gemini 3 Flash (Preview)) |
| 5 | Gemini 3 Pro (Preview) | 85.18 | #66 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 84.68 | #300 |
| 7 | Claude Sonnet 4.6 | 83.48 | #90 |
| 8 | GPT-5 (2025-08-07) (High) | 83.46 | |
| 9 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 80.77 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 10 | Gemma 4 31B (IT) | 80.62 | #176 |
| 11 | Gemini 2.5 Pro | 80.57 | #152 |
| 12 | Mistral Small 3.1 | 80.14 | #610 |
| 13 | Llama 3.1 405B Instruct FP8 | 80.03 | #389 |
| 14 | Qwen 3.5 35B A3B FP8 | 79.8 | #362 |
| 15 | GPT-5 | 79.64 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-dutch-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.