EuroEval Norwegian NLU - NorNE NB: leaderboard
The "NorNE NB" subtask of EuroEval Norwegian NLU. Norwegian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 396 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 4B 2507 (Thinking) | 86.13 | #538 (Qwen 3 4B 2507) |
| 2 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 84.36 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 3 | Claude Sonnet 4.5 (Non-reasoning) | 82.94 | #142 (Claude Sonnet 4.5) |
| 4 | GPT-5.4 Mini (2026-03-17) (High) | 82.75 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 5 | Qwen 3 Next 80B A3B (Thinking) | 82.13 | #320 (Qwen 3 Next 80B A3B) |
| 6 | Llama 3.1 405B Instruct FP8 | 82.1 | #389 |
| 7 | Gemma 4 31B (IT) | 81.87 | #176 |
| 8 | QwQ-32B | 81.55 | #421 |
| 9 | GLM 4.5 Air (Thinking) | 81.39 | #392 (GLM 4.5 Air) |
| 10 | Claude Sonnet 4.5 (Thinking) | 80.47 | #142 (Claude Sonnet 4.5) |
| 11 | GPT-5 (2025-08-07) (High) | 80.22 | |
| 12 | Llama 3.1 70B | 80.07 | #592 |
| 13 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 79.96 | #679 |
| 14 | Gemma 4 26B A4B (IT) | 79.92 | #297 |
| 15 | Llama 3.1 70B Instruct | 79.86 | #561 |
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-norne-nb · How It Works · Data refreshed daily, snapshot 2026-10-20.