EuroEval Norwegian NLU - Norec: leaderboard
The "Norec" subtask of EuroEval Norwegian NLU. Norwegian-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: Estimated already saturated. 400 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 27B (IT) | 67.35 | #645 |
| 2 | Gemma 2 27B | 65.57 | #806 |
| 3 | Gemma 4 26B A4B (IT) | 65.23 | #297 |
| 4 | Gemma 4 31B (IT) | 65.09 | #176 |
| 5 | Gemma 3 27B (IT) | 64.97 | #523 |
| 6 | Llama 3.1 405B Instruct FP8 | 64.42 | #389 |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 64.09 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemini 3 Pro (Preview) | 63.9 | #66 |
| 9 | Llama 3.1 70B | 63.88 | #592 |
| 10 | Llama 4 Scout Instruct | 63.43 | #539 |
| 11 | Gemma 3 12B (IT) | 63.08 | #664 |
| 12 | Gemma 2 9B | 62.9 | #958 |
| 13 | Claude Sonnet 4.6 | 62.27 | #90 |
| 14 | Gemma 2 9B (IT) | 61.7 | #788 |
| 15 | GPT-5 Mini (2025-08-07) | 61.55 | #172 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-norwegian-nlu-norec · How It Works · Data refreshed daily, snapshot 2026-10-20.