EuroEval Dutch NLU - DBRD: leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 450 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 94.61 |
| 2 | Gemini 3 Pro (Preview) | 94.61 |
| 3 | GPT-4.1 | 94.02 |
| 4 | GPT-5.4 Mini (Medium) | 93.85 |
| 5 | Claude Sonnet 4.5 (Non-reasoning) | 93.73 |
| 6 | Gemini 2.5 Flash (Preview 04-17) | 93.67 |
| 7 | Grok 4.1 Fast (Reasoning) | 93.57 |
| 8 | GPT-5 | 93.56 |
| 9 | O3 (2025-04-16) | 93.56 |
| 10 | Claude Sonnet 4.5 (Thinking) | 93.44 |
| 11 | GPT-5.4 Mini (High) | 93.38 |
| 12 | Gemma 4 31B (IT) | 93.37 |
| 13 | GPT-5 Mini (High) | 93.15 |
| 14 | GPT-5 (High) | 93.03 |
| 15 | Qwen 3 235B A22B 2507 Instruct | 93.01 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-dutch-nlu-dbrd · How It Works · Data refreshed daily, snapshot 2026-09-05.