Evals for Every Language - Dutch (nl): leaderboard
Average score across evaluation tasks in Dutch (nl), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around May 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 79.2 | #58 |
| 2 | Gemini 3.1 Flash Lite | 78.99 | #191 |
| 3 | Claude Opus 4.8 | 77.76 | #37 |
| 4 | Claude Opus 4.7 | 77.75 | #49 |
| 5 | Claude Sonnet 4.6 | 77.39 | #90 |
| 6 | Claude Sonnet 4.5 | 75.9 | #142 |
| 7 | Qwen 3.6 Plus | 75.35 | #120 |
| 8 | Grok 4.20 | 75.23 | #175 |
| 9 | Claude Sonnet 4 | 75.17 | #199 |
| 10 | GPT-5.3 | 74.58 | #103 |
| 11 | Gemma 3 27B (IT) | 74.37 | #523 |
| 12 | Gemini 2.5 Pro | 73.86 | #152 |
| 13 | Ministral 3 14B | 73.64 | #650 |
| 14 | Claude Haiku 4.5 | 73.62 | #280 |
| 15 | Command A | 73.46 | #508 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-nl · How It Works · Data refreshed daily, snapshot 2026-10-20.