EuroEval Faroese NLU - FoQA — leaderboard
Metric: Reading comprehension Score (%). Source: euroeval.com. 393 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Ministral 3 14B | 79.94 |
| 2 | Mistral Small 3.2 | 79.92 |
| 3 | Llama 3.1 405B Instruct FP8 | 79.74 |
| 4 | Magistral Small | 79.56 |
| 5 | Mistral Small 3.1 | 79.48 |
| 6 | Llama 3.1 70B | 79.34 |
| 7 | Ministral-3-14B-Reasoning-2512 | 79.31 |
| 8 | Ministral-3-14B-Instruct-2512 | 78.86 |
| 9 | Gemma 2 9B (IT) | 78.56 |
| 10 | gemma-3-12B-pt | 77.27 |
| 11 | gemma-3-27B-pt | 77.23 |
| 12 | GPT-5.4 Mini (Non-reasoning) | 77.19 |
| 13 | Gemini 2.5 Flash Lite (Non-reasoning) | 76.6 |
| 14 | GPT-5 Mini (Minimal) | 76.55 |
| 15 | GPT-4.1 | 76.47 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-faroese-nlu-foqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.