EuroEval Norwegian Common Sense Reasoning: leaderboard
EuroEval's Norwegian common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Norwegian, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around April 2027. 431 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 92.76 | #90 |
| 2 | Gemini 2.5 Pro | 91.24 | #152 |
| 3 | GPT-5 | 91.07 | #98 |
| 4 | O3 (2025-04-16) | 90.51 | #121 |
| 5 | Gemma 4 31B (IT) | 90.45 | #176 |
| 6 | Claude Sonnet 4.5 (Thinking) | 90.45 | #142 (Claude Sonnet 4.5) |
| 7 | Grok 3 Mini | 90.07 | #281 |
| 8 | GPT-5 Nano | 89.34 | #425 |
| 9 | Claude 3.7 Sonnet (20250219) (Thinking) | 89.01 | #201 (Claude 3.7 Sonnet (20250219)) |
| 10 | GPT-4.1 Mini | 88.9 | #355 |
| 11 | Gemini 2.5 Flash Lite (Thinking) | 88.7 | #422 (Gemini 2.5 Flash Lite) |
| 12 | Gemini 1.5 Flash-8B (001) | 88.45 | #791 |
| 13 | Gemini 3 Pro (Preview) | 88.36 | #66 |
| 14 | GPT-5 (2025-08-07) (High) | 88.36 | |
| 15 | Gemini 2.5 Flash (Non-reasoning) | 88.29 | #245 (Gemini 2.5 Flash) |
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-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.