EuroEval Icelandic NLU: leaderboard
Icelandic-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: NLU Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 393 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 65.84 | #66 |
| 2 | GPT-5 (2025-08-07) (High) | 63.3 | |
| 3 | GPT-5 | 62.61 | #98 |
| 4 | Claude Sonnet 4.5 (Thinking) | 61.77 | #142 (Claude Sonnet 4.5) |
| 5 | Gemini 3.1 Flash Lite (Preview) | 61.04 | #194 |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 60.31 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 59.95 | #82 (Gemini 3 Flash (Preview)) |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 59.79 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Claude 3.7 Sonnet (20250219) (Thinking) | 59.6 | #201 (Claude 3.7 Sonnet (20250219)) |
| 10 | O3 (2025-04-16) | 59.47 | #121 |
| 11 | Gemini 2.5 Flash (Thinking) | 56.67 | #245 (Gemini 2.5 Flash) |
| 12 | Gemini 2.5 Flash (Preview 04-17) | 56.24 | #237 |
| 13 | GPT-5.2 | 56.02 | #110 |
| 14 | Qwen 3.5 35B A3B Base | 55.97 | #310 |
| 15 | O4 Mini (2025-04-16) | 55.92 | #179 |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.