Grip on LLMs - Dutch tinyTruthfulQA: leaderboard
Metric: Accuracy (%; GP-IRT estimate from 100 tinyBenchmarks items, Dutch machine translation). Source: arxiv.org. 31 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Small 3 | 78 |
| 2 | GPT-5 Mini | 77 |
| 3 | Mistral Medium 3 | 76 |
| 4 | GPT-5 | 75 |
| 5 | Qwen 3 32B | 71 |
| 6 | DeepSeek R1 Distill Qwen 32B | 70 |
| 7 | GPT-4o | 69 |
| 8 | GPT-5 Nano | 64 |
| 9 | Gemma 3 27B (IT) | 63 |
| 10 | Mistral Large 3 | 63 |
| 11 | Gemma 3 12B (IT) | 62 |
| 12 | GPT-OSS-20B | 62 |
| 13 | GPT-4o Mini | 61 |
| 14 | aya-expanse-32B | 61 |
| 15 | Qwen 3 8B | 59 |
Interactive version: theaggregate.ai/benchmark?slug=grip-on-llms-dutch-tinytruthfulqa · How It Works · Data refreshed daily, snapshot 2026-09-19.