EuroEval Norwegian NLU - ScaLA NB: leaderboard
The "ScaLA 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: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 397 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) (Thinking) | 81.62 | #201 (Claude 3.7 Sonnet (20250219)) |
| 2 | Gemini 2.5 Pro | 79.04 | #152 |
| 3 | GPT-4.1 | 78.88 | #248 |
| 4 | O3 (2025-04-16) | 77.07 | #121 |
| 5 | Gemini 3 Flash (Preview) (Non-reasoning) | 76.61 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Gemini 2.5 Pro (Preview 03-25) | 76.24 | #123 |
| 7 | Gemini 3 Pro (Preview) | 75.23 | #66 |
| 8 | GPT-4.1 Mini | 74.03 | #355 |
| 9 | Llama 3.1 405B | 73.89 | #466 |
| 10 | Gemini 2.5 Flash (Thinking) | 73.81 | #245 (Gemini 2.5 Flash) |
| 11 | Gemini 2.5 Flash (Preview 04-17) | 72.42 | #237 |
| 12 | GPT-5 Mini (2025-08-07) (High) | 72.25 | #172 (GPT-5 Mini (2025-08-07)) |
| 13 | Gemini 3.1 Flash Lite (Preview) | 71.65 | #194 |
| 14 | GPT-5.2 | 71.37 | #110 |
| 15 | Gemini 2.5 Flash Lite (Thinking) | 71.27 | #422 (Gemini 2.5 Flash Lite) |
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-scala-nb · How It Works · Data refreshed daily, snapshot 2026-10-20.