EuroEval Faroese NLU - ScaLA FO: leaderboard
EuroEval's Faroese natural-language-understanding score — aggregate over the EuroEval Faroese understanding tasks (reading comprehension, linguistic acceptability, NER), from the EuroEval European language model benchmark suite.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Around 2030. 406 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 54.6 | #66 |
| 2 | Gemini 2.5 Flash (Preview 04-17) | 51.83 | #237 |
| 3 | GPT-5 (2025-08-07) (High) | 50.38 | |
| 4 | Claude 3.7 Sonnet (20250219) (Thinking) | 49.81 | #201 (Claude 3.7 Sonnet (20250219)) |
| 5 | Gemini 3.1 Flash Lite (Preview) | 45.52 | #194 |
| 6 | Gemini 2.5 Pro | 45.33 | #152 |
| 7 | GPT-5.4 Mini (2026-03-17) (High) | 44.49 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 8 | GPT-5 | 42.6 | #98 |
| 9 | Gemini 3 Flash (Preview) (Thinking) | 42.19 | #82 (Gemini 3 Flash (Preview)) |
| 10 | Claude Sonnet 4.5 (Thinking) | 38.51 | #142 (Claude Sonnet 4.5) |
| 11 | Gemini 2.5 Flash (Thinking) | 36.77 | #245 (Gemini 2.5 Flash) |
| 12 | Qwen 3 235B A22B 2507 Instruct | 35.75 | #300 |
| 13 | Grok 4.1 Fast (Reasoning) | 35.21 | #217 (Grok 4.1 Fast) |
| 14 | Gemma 4 31B (IT) | 34.48 | #176 |
| 15 | Grok 3 Mini | 34.07 | #281 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-faroese-nlu-scala-fo · How It Works · Data refreshed daily, snapshot 2026-10-20.