EuroEval Dutch NLU: leaderboard
Dutch-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: NLU Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 339 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 405B | 80.98 | #466 |
| 2 | Gemma 4 31B (IT) | 80.34 | #176 |
| 3 | Gemini 3 Pro (Preview) | 79.74 | #66 |
| 4 | Claude Sonnet 4.5 (Thinking) | 79.5 | #142 (Claude Sonnet 4.5) |
| 5 | Gemini 3 Flash (Preview) (Non-reasoning) | 79.44 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Gemini 3 Flash (Preview) (Thinking) | 79.13 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemini 3.1 Flash Lite (Preview) | 78.64 | #194 |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 78.25 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Qwen 3.5 35B A3B FP8 | 78.11 | #362 |
| 10 | Claude Sonnet 4.5 (Non-reasoning) | 76.59 | #142 (Claude Sonnet 4.5) |
| 11 | Qwen 3.5 35B A3B Base | 76.59 | #310 |
| 12 | Qwen 3 235B A22B 2507 Instruct | 76.37 | #300 |
| 13 | Llama 3.1 70B | 76.28 | #592 |
| 14 | Claude Sonnet 4.6 | 75.9 | #90 |
| 15 | O3 (2025-04-16) | 75.62 | #121 |
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-nlu · How It Works · Data refreshed daily, snapshot 2026-10-20.