EuroEval Norwegian Knowledge — leaderboard
Metric: Knowledge Average Score (%). Source: euroeval.com. 432 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 87.61 |
| 2 | Gemini 3 Pro (Preview) | 87.01 |
| 3 | GPT-5 | 86.56 |
| 4 | GPT-5 (High) | 85.34 |
| 5 | Gemini 2.5 Pro (Preview 03-25) | 85.09 |
| 6 | O3 (2025-04-16) | 84.13 |
| 7 | Gemini 3 Flash (Preview) (Non-reasoning) | 82.94 |
| 8 | GPT-5.4 Mini (High) | 78.03 |
| 9 | GPT-5.4 Mini (Medium) | 76.09 |
| 10 | Claude Sonnet 4.5 (Thinking) | 74.78 |
| 11 | GPT-4.1 | 72.89 |
| 12 | GPT-5 Mini (High) | 71.74 |
| 13 | Gemini 2.5 Flash (Preview 04-17) | 71.49 |
| 14 | Grok 3 | 71.26 |
| 15 | Claude 3.7 Sonnet (20250219) (Thinking) | 71.04 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-norwegian-knowledge · How the rankings work · Data refreshed daily, snapshot 2026-07-22.