EuroEval Norwegian NLU - Norquad: leaderboard
The "Norquad" subtask of EuroEval Norwegian NLU. Norwegian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Character F1 (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 383 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 405B | 79.66 | #466 |
| 2 | Llama 3.1 70B | 78.48 | #592 |
| 3 | Qwen 3 32B (Non-reasoning) | 78.03 | #443 (Qwen 3 32B) |
| 4 | Magistral Small 1.2 | 77.06 | #570 |
| 5 | gemma-3-27B-pt | 76.93 | #502 |
| 6 | Ministral-3-14B-Reasoning-2512 | 76.44 | #540 |
| 7 | Mistral Small 3.1 | 76.2 | #610 |
| 8 | Mistral Small 3.2 | 76.1 | #605 |
| 9 | Qwen 3 14B (Non-reasoning) | 75.51 | #537 (Qwen 3 14B) |
| 10 | Gemma 2 27B | 75.27 | #806 |
| 11 | Gemini 3 Pro (Preview) | 75.22 | #66 |
| 12 | Llama 3.1 70B Instruct | 74.92 | #561 |
| 13 | Llama 2 70B Base | 74.86 | #1025 |
| 14 | Gemma 3n E4B | 74.34 | #878 |
| 15 | Claude Sonnet 4.5 (Non-reasoning) | 74.22 | #142 (Claude Sonnet 4.5) |
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-norquad · How It Works · Data refreshed daily, snapshot 2026-10-20.