EuroEval Icelandic NLU - ScaLA IS: leaderboard
The "ScaLA IS" subtask of EuroEval Icelandic NLU. Icelandic-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Around August 2028. 398 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 69.88 | #66 |
| 2 | Claude 3.7 Sonnet (20250219) (Thinking) | 62.13 | #201 (Claude 3.7 Sonnet (20250219)) |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 61.88 | #82 (Gemini 3 Flash (Preview)) |
| 4 | GPT-5 (2025-08-07) (High) | 59.65 | |
| 5 | Gemini 3.1 Flash Lite (Preview) | 59.17 | #194 |
| 6 | GPT-5 | 57.81 | #98 |
| 7 | Claude Sonnet 4.5 (Thinking) | 56.61 | #142 (Claude Sonnet 4.5) |
| 8 | Gemini 3 Flash (Preview) (Thinking) | 56.16 | #82 (Gemini 3 Flash (Preview)) |
| 9 | O3 (2025-04-16) | 55.32 | #121 |
| 10 | Gemini 2.5 Flash (Thinking) | 53.96 | #245 (Gemini 2.5 Flash) |
| 11 | O4 Mini (2025-04-16) | 53.35 | #179 |
| 12 | Gemini 2.5 Pro | 53.03 | #152 |
| 13 | Gemini 2.5 Pro (Preview 03-25) | 51.46 | #123 |
| 14 | GPT-5 Mini (2025-08-07) (High) | 50.58 | #172 (GPT-5 Mini (2025-08-07)) |
| 15 | GPT-4.1 | 50.04 | #248 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-icelandic-nlu-scala-is · How It Works · Data refreshed daily, snapshot 2026-10-20.