EuroEval Norwegian NLU - NorNE NB — leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 396 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 4B 2507 (Thinking) | 86.13 |
| 2 | Claude Sonnet 4.5 (Non-reasoning) | 82.94 |
| 3 | GPT-5.4 Mini (High) | 82.75 |
| 4 | GPT-5.4 Mini (Medium) | 82.16 |
| 5 | Qwen 3 Next 80B A3B (Thinking) | 82.13 |
| 6 | Llama 3.1 405B Instruct FP8 | 82.1 |
| 7 | Gemma 4 31B (IT) | 81.87 |
| 8 | QwQ-32B | 81.55 |
| 9 | Claude Sonnet 4.5 (Thinking) | 80.47 |
| 10 | GPT-5 (High) | 80.22 |
| 11 | Llama 3.1 70B | 80.07 |
| 12 | Gemma 4 26B A4B (IT) | 79.92 |
| 13 | Llama 3.1 70B Instruct | 79.86 |
| 14 | Gemini 3 Pro (Preview) | 79.49 |
| 15 | GPT-5 | 79.44 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-norwegian-nlu-norne-nb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.