EuroEval Dutch NLU - DBRD: leaderboard
The "DBRD" subtask of EuroEval Dutch NLU. Dutch-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 450 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 94.61 | #110 |
| 2 | Gemini 3 Pro (Preview) | 94.61 | #66 |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 94.09 | #82 (Gemini 3 Flash (Preview)) |
| 4 | GPT-4.1 | 94.02 | #248 |
| 5 | Claude Sonnet 4.5 (Non-reasoning) | 93.73 | #142 (Claude Sonnet 4.5) |
| 6 | Gemini 2.5 Flash (Preview 04-17) | 93.67 | #237 |
| 7 | Grok 4.1 Fast (Reasoning) | 93.57 | #217 (Grok 4.1 Fast) |
| 8 | GPT-5 | 93.56 | #98 |
| 9 | O3 (2025-04-16) | 93.56 | #121 |
| 10 | Claude Sonnet 4.5 (Thinking) | 93.44 | #142 (Claude Sonnet 4.5) |
| 11 | GPT-5.4 Mini (2026-03-17) (High) | 93.38 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 12 | Gemma 4 31B (IT) | 93.37 | #176 |
| 13 | GPT-5 Mini (2025-08-07) (High) | 93.15 | #172 (GPT-5 Mini (2025-08-07)) |
| 14 | GPT-5 (2025-08-07) (High) | 93.03 | |
| 15 | Qwen 3 235B A22B 2507 Instruct | 93.01 | #300 |
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-dbrd · How It Works · Data refreshed daily, snapshot 2026-10-20.