EuroEval Dutch NLU - ScaLA NL — leaderboard
Metric: Linguistic acceptability Score (%). Source: euroeval.com. 332 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite (Preview) | 77.57 |
| 2 | Gemini 3 Pro (Preview) | 77.07 |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 75.69 |
| 4 | Claude 3.7 Sonnet (20250219) (Thinking) | 74.66 |
| 5 | Gemini 2.5 Pro | 73.47 |
| 6 | Llama 3.1 405B | 72.93 |
| 7 | Gemini 2.5 Pro (Preview 03-25) | 70.76 |
| 8 | Claude Sonnet 4.5 (Thinking) | 70.03 |
| 9 | GPT-5.4 Mini (High) | 69.61 |
| 10 | Llama 3.1 405B Instruct FP8 | 69.11 |
| 11 | Gemma 4 31B (IT) | 69.01 |
| 12 | O3 (2025-04-16) | 68.86 |
| 13 | Qwen 3 235B A22B 2507 Instruct | 68.5 |
| 14 | Gemini 2.5 Flash (Preview 04-17) | 68.47 |
| 15 | Claude Sonnet 4.6 | 68.23 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-dutch-nlu-scala-nl · How the rankings work · Data refreshed daily, snapshot 2026-07-22.