EuroEval Dutch: leaderboard
Dutch-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 351 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 405B | 78.43 | #466 |
| 2 | GPT-5 (2025-08-07) (High) | 78.3 | |
| 3 | GPT-5 | 77.71 | #98 |
| 4 | Gemini 2.5 Pro | 77.01 | #152 |
| 5 | O3 (2025-04-16) | 76.66 | #121 |
| 6 | Claude 3.7 Sonnet (20250219) (Thinking) | 75.35 | #201 (Claude 3.7 Sonnet (20250219)) |
| 7 | Qwen 3 Next 80B A3B Instruct | 75.23 | #368 |
| 8 | Qwen 3 235B A22B | 75.16 | #313 |
| 9 | Qwen 3 235B A22B 2507 Instruct | 75.15 | #300 |
| 10 | Gemini 2.5 Pro (Preview 03-25) | 74.94 | #123 |
| 11 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 74.51 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 12 | QwQ-32B | 73.98 | #421 |
| 13 | Gemini 2.5 Flash (Non-reasoning) | 73.91 | #245 (Gemini 2.5 Flash) |
| 14 | O4 Mini (2025-04-16) | 73.52 | #179 |
| 15 | Llama 3.1 405B Instruct FP8 | 73.33 | #389 |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.