EuroEval Faroese NLU - FoSent: 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: Estimated already saturated. 400 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 91.61 | #123 |
| 2 | Gemini 2.5 Flash (Preview 04-17) | 84.89 | #237 |
| 3 | Gemini 3 Pro (Preview) | 83.1 | #66 |
| 4 | Gemini 3 Flash (Preview) (Thinking) | 82.77 | #82 (Gemini 3 Flash (Preview)) |
| 5 | O3 (2025-04-16) | 81 | #121 |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 79.61 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Claude Sonnet 4.6 | 77.8 | #90 |
| 8 | GPT-4.1 | 77.78 | #248 |
| 9 | GPT-5 Mini (2025-08-07) | 77.66 | #172 |
| 10 | Gemma 4 31B (IT) | 76.96 | #176 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 75.3 | #194 |
| 12 | Claude Sonnet 4.5 (Non-reasoning) | 74.64 | #142 (Claude Sonnet 4.5) |
| 13 | Claude Sonnet 4.5 (Thinking) | 74.33 | #142 (Claude Sonnet 4.5) |
| 14 | GPT-5.4 Mini (2026-03-17) (High) | 73.95 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 15 | Grok 2 (1212) | 73.84 | #496 |
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-fosent · How It Works · Data refreshed daily, snapshot 2026-10-20.